#126 by GitHub stars
google/elephant-goldfish-model
Open-source skills for designing and reviewing software with AI agents
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
distributions/claude/skills/egm-bootstrap/SKILL.md
Week of Nov 2, 2026 · +3 / −3 lines
Before Instructions only → After Local scripts
05f8984cb6e0 → 113a3afc44e8
- 57 3. **Temporary File Isolation**: Parallel workers sharing the workspace must
- 58 perform all status tracking, check-pointing, and log writing in independent,
- 59 worker-specific directories outside the project repository workspace.
+ 57 3. **Temporary File Isolation**: Each worker keeps its status, checkpoint,
+ 58 and log files in its own directory outside the workspace (host scratch or
+ 59 `mktemp -d`), never a fixed, shared path. If neither exists, skip them.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 05f8984cb6e0
No earlier version was observed for comparison.
distributions/claude/skills/egm-brainstorm/SKILL.md
Week of Nov 2, 2026 · +15 / −10 lines
Before Instructions only → After Local scripts
05f8984cb6e0 → 113a3afc44e8
- 10 /egm-draft.
+ 10 egm-draft.
- 105 1. **Check for Concept Foundation**: Verify if the user provided an initial
+ 105 1. **Check for Concept Foundation & Author Identity**: Verify if the user provided an initial
- 107 they want to brainstorm.
+ 107 they want to brainstorm. Resolve the brief's `Author` from `git config user.name`,
+ 108 then `GIT_AUTHOR_NAME`; if neither is set, ask in chat.
- 201 [Each option rejected during ideation, with the reason. `/egm-draft` copies
+ 202 [Each option rejected during ideation, with the technical reason (e.g. "Rejected by author: <reason>"). Do not attribute a rejection to a maintainer without linking their issue, discussion, or PR. `/egm-draft` copies
- 234 "Proceed to /egm-draft (Initialize formal design document)",
+ 235 "Proceed to egm-draft (Initialize formal design document)",
- 251 initiated by running `/egm-draft docs/designs/<feature_name>.md`.
- 252 * **Option 1: `Proceed to /egm-draft (Initialize formal design
+ 252 initiated by starting the `egm-draft` skill on
+ 253 `docs/designs/<feature_name>.md` with the host's command form (for
+ 254 example `/egm:egm-draft docs/designs/<feature_name>.md` in Claude
+ 255 Code and agy CLI, or the skill picker in Codex).
+ 256 * **Option 1: `Proceed to egm-draft (Initialize formal design
- 256 * Instruct the user to run `/egm-draft` (or activate the `egm-draft`
- 257 skill), noting that `/egm-draft` automatically ingests
- 258 `concepts_brief.md` as its Priority 1 intake source.
+ 260 * Instruct the user to start the `egm-draft` skill with the host's
+ 261 command form (for example `/egm:egm-draft` in Claude Code and agy
+ 262 CLI, or the skill picker in Codex), noting that it automatically
+ 263 ingests `concepts_brief.md` as its Priority 1 intake source.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 05f8984cb6e0
No earlier version was observed for comparison.
distributions/claude/skills/egm-draft/SKILL.md
Week of Nov 2, 2026 · +16 / −9 lines
Before Instructions only → After Instructions only
05f8984cb6e0 → 113a3afc44e8
- 63 13. **Owner Decides Architecture**: When a design decision has more than one
+ 63 13. **Author Decides Architecture**: When a design decision has more than one
- 66 trade-offs, and the conditions under which it fails, and ask the owner to
+ 66 trade-offs, and the conditions under which it fails, and ask the author to
- 68 default, or pick one. If the owner asks you to choose ("just pick one"),
+ 68 default, or pick one. If the author asks you to choose ("just pick one"),
- 158 technical context, or offer to launch `/egm-brainstorm`.
+ 158 technical context, or suggest that the user start the `egm-brainstorm`
+ 159 skill with the host's command form (for example `/egm:egm-brainstorm`
+ 160 in Claude Code and agy CLI, or the skill picker in Codex).
+ 164 5. **Resolve Author**: Use the `Author` from the ingested brief if it has one.
+ 165 Otherwise use `git config user.name`, then `GIT_AUTHOR_NAME`. If neither is
+ 166 set, prompt the user in chat. Record it in the document header.
+ 211 Document author decisions as `Rejected by author: [technical rationale]`.
+ 212 Do NOT state `Rejected by maintainer` unless quoting an upstream maintainer
+ 213 issue, discussion, or PR URL.
- 310 that the user review the document with:
- 311
- 312 ```markdown
- 313 `egm-review` <DESIGN_PATH>
- 314 ```
+ 318 that the user review it by starting the `egm-review` skill on
+ 319 `<DESIGN_PATH>` with the host's command form (for example
+ 320 `/egm:egm-review <DESIGN_PATH>` in Claude Code and agy CLI, or the skill
+ 321 picker in Codex).
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 05f8984cb6e0
No earlier version was observed for comparison.
distributions/claude/skills/egm-drift-report/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Local scripts
05f8984cb6e0 → 113a3afc44e8
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 05f8984cb6e0
No earlier version was observed for comparison.
distributions/claude/skills/egm-resolve/SKILL.md
Week of Nov 2, 2026 · +1 / −1 lines
Before Instructions only → After Instructions only
05f8984cb6e0 → 113a3afc44e8
- 98 ### [Issue 1] [`[ReviewerPersona]`] - Severity: [High | Medium | Low]
+ 98 ### [Issue 1] [`[ReviewerPersona]`] - Severity: [Blocker | Major | Nit]
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 05f8984cb6e0
No earlier version was observed for comparison.
distributions/claude/skills/egm-review/SKILL.md
Week of Nov 2, 2026 · +33 / −11 lines
Before Instructions only → After Instructions only
05f8984cb6e0 → 113a3afc44e8
- 75 baseline. If omitted, the system defaults to no additional context (but
- 76 always automatically reads files linked or referenced in the design doc).
+ 75 baseline. If omitted, it holds only the linked files that Step 1.3 adds.
- 92 2. Once `TargetFile` is provided, verify if `GoldfishContext` is provided (or
- 93 if the user explicitly stated in their prompt to proceed with no additional
- 94 context). If missing:
+ 91 2. Once `TargetFile` is provided, verify if `GoldfishContext` is provided (an
+ 92 empty list counts as provided, as does the user explicitly stating in their
+ 93 prompt to proceed with no additional context). If missing:
- 97 * Clarify that reviewers **always automatically read** files explicitly
- 98 mentioned or linked in the target design document itself.
+ 96 * Clarify that linked files inside the working directory are added
+ 97 automatically, and that other links and URLs need approval.
+ 101 3. **Linked Files (run later)**: Do not run this during intake. Run it once,
+ 102 after the Step 2 preset is chosen and right before the first stage that
+ 103 takes `GoldfishContext` (any stage but Stage 6), in any flow including
+ 104 `uninterrupted`. Read `TargetFile`, skip anchor-only links (`#...`), drop
+ 105 the `#fragment` from other links, and resolve each relative link against
+ 106 the design document's folder. Add each link whose real path (after
+ 107 following symbolic links) stays inside the working directory to
+ 108 `GoldfishContext`, skipping files that do not exist. If any link resolves
+ 109 outside the working directory or is a URL, list those links in chat as
+ 110 regular text, ask which to include, and end your turn; if no one can
+ 111 answer, as in a headless run, leave them all out and keep going. Add only
+ 112 approved ones and tell the user which were left out. Some reviewers cannot
+ 113 open URLs, so save the raw page of each URL in `GoldfishContext` as a new
+ 114 file in the working directory (or your harness's artifact directory) and
+ 115 pass its absolute path instead. If a page cannot be saved, ask the user for
+ 116 a local copy and end your turn; if no one can answer, as in a headless run,
+ 117 leave it out, tell the user, and keep going. Pass
+ 118 `GoldfishContext` to every stage except Stage 6, which reads the document
+ 119 alone; tell any synthesizer to give these files to each reviewer.
+ 269 * If Step 1.3 has run, apply its rules to links added since then.
- 266 harness's artifact directory, if it has one):
+ 285 harness's artifact directory, if it has one). Pass `GoldfishContext` to
+ 286 every step except Step 6.
+ 323 In both Stage 5 and Stage 8, pass `GoldfishContext`.
- 351 `FeatureRange` with reviewers `[egm-design, egm-structural, egm-style]` and
+ 372 `FeatureRange` with reviewers `[egm-design, egm-structural, egm-style]`,
- 353 "feature-spec-standard"}`.
+ 374 "feature-spec-standard"}`, and `GoldfishContext`.
- 381 "egm-codebase-details": "implementation-readiness-standard"}`.
+ 402 "egm-codebase-details": "implementation-readiness-standard"}`, and
+ 403 `GoldfishContext`.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 05f8984cb6e0
No earlier version was observed for comparison.
distributions/claude/skills/egm-review-loop/SKILL.md
Week of Nov 2, 2026 · +11 / −3 lines
Before Instructions only → After Local scripts
05f8984cb6e0 → 113a3afc44e8
- 57 documentation URLs) fed to reviewers to establish their baseline.
+ 57 documentation URLs) fed to reviewers to establish their baseline. An empty
+ 58 list from the caller counts as provided; do not ask for it again. Some
+ 59 reviewers cannot open URLs, so before the first round save the raw page of
+ 60 each URL as a new file in the working directory (or your harness's artifact
+ 61 directory) and pass its absolute path instead. If a page cannot be saved,
+ 62 ask the user for a local copy and end your turn; if no one can answer,
+ 63 as in a headless run, leave it out, tell the user, and keep going.
- 118 conversation. Pass it the Failed Reviewers rule below. Its summary must
- 119 give a status, `completed` or `not run`, for each requested reviewer.
+ 124 conversation. Pass it the Failed Reviewers rule below and
+ 125 `GoldfishContext`, and tell it to give those files to each reviewer.
+ 126 Its summary must give a status, `completed` or `not run`, for each
+ 127 requested reviewer.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 05f8984cb6e0
No earlier version was observed for comparison.
skills/egm-bootstrap/SKILL.md
Week of Nov 2, 2026 · +3 / −3 lines
Before Instructions only → After Local scripts
05f8984cb6e0 → 113a3afc44e8
- 57 3. **Temporary File Isolation**: Parallel workers sharing the workspace must
- 58 perform all status tracking, check-pointing, and log writing in independent,
- 59 worker-specific directories outside the project repository workspace.
+ 57 3. **Temporary File Isolation**: Each worker keeps its status, checkpoint,
+ 58 and log files in its own directory outside the workspace (host scratch or
+ 59 `mktemp -d`), never a fixed, shared path. If neither exists, skip them.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 05f8984cb6e0
No earlier version was observed for comparison.
skills/egm-brainstorm/SKILL.md
Week of Nov 2, 2026 · +15 / −10 lines
Before Instructions only → After Local scripts
05f8984cb6e0 → 113a3afc44e8
- 10 /egm-draft.
+ 10 egm-draft.
- 105 1. **Check for Concept Foundation**: Verify if the user provided an initial
+ 105 1. **Check for Concept Foundation & Author Identity**: Verify if the user provided an initial
- 107 they want to brainstorm.
+ 107 they want to brainstorm. Resolve the brief's `Author` from `git config user.name`,
+ 108 then `GIT_AUTHOR_NAME`; if neither is set, ask in chat.
- 201 [Each option rejected during ideation, with the reason. `/egm-draft` copies
+ 202 [Each option rejected during ideation, with the technical reason (e.g. "Rejected by author: <reason>"). Do not attribute a rejection to a maintainer without linking their issue, discussion, or PR. `/egm-draft` copies
- 234 "Proceed to /egm-draft (Initialize formal design document)",
+ 235 "Proceed to egm-draft (Initialize formal design document)",
- 251 initiated by running `/egm-draft docs/designs/<feature_name>.md`.
- 252 * **Option 1: `Proceed to /egm-draft (Initialize formal design
+ 252 initiated by starting the `egm-draft` skill on
+ 253 `docs/designs/<feature_name>.md` with the host's command form (for
+ 254 example `/egm:egm-draft docs/designs/<feature_name>.md` in Claude
+ 255 Code and agy CLI, or the skill picker in Codex).
+ 256 * **Option 1: `Proceed to egm-draft (Initialize formal design
- 256 * Instruct the user to run `/egm-draft` (or activate the `egm-draft`
- 257 skill), noting that `/egm-draft` automatically ingests
- 258 `concepts_brief.md` as its Priority 1 intake source.
+ 260 * Instruct the user to start the `egm-draft` skill with the host's
+ 261 command form (for example `/egm:egm-draft` in Claude Code and agy
+ 262 CLI, or the skill picker in Codex), noting that it automatically
+ 263 ingests `concepts_brief.md` as its Priority 1 intake source.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 05f8984cb6e0
No earlier version was observed for comparison.
skills/egm-draft/SKILL.md
Week of Nov 2, 2026 · +16 / −9 lines
Before Instructions only → After Instructions only
05f8984cb6e0 → 113a3afc44e8
- 63 13. **Owner Decides Architecture**: When a design decision has more than one
+ 63 13. **Author Decides Architecture**: When a design decision has more than one
- 66 trade-offs, and the conditions under which it fails, and ask the owner to
+ 66 trade-offs, and the conditions under which it fails, and ask the author to
- 68 default, or pick one. If the owner asks you to choose ("just pick one"),
+ 68 default, or pick one. If the author asks you to choose ("just pick one"),
- 158 technical context, or offer to launch `/egm-brainstorm`.
+ 158 technical context, or suggest that the user start the `egm-brainstorm`
+ 159 skill with the host's command form (for example `/egm:egm-brainstorm`
+ 160 in Claude Code and agy CLI, or the skill picker in Codex).
+ 164 5. **Resolve Author**: Use the `Author` from the ingested brief if it has one.
+ 165 Otherwise use `git config user.name`, then `GIT_AUTHOR_NAME`. If neither is
+ 166 set, prompt the user in chat. Record it in the document header.
+ 211 Document author decisions as `Rejected by author: [technical rationale]`.
+ 212 Do NOT state `Rejected by maintainer` unless quoting an upstream maintainer
+ 213 issue, discussion, or PR URL.
- 310 that the user review the document with:
- 311
- 312 ```markdown
- 313 `egm-review` <DESIGN_PATH>
- 314 ```
+ 318 that the user review it by starting the `egm-review` skill on
+ 319 `<DESIGN_PATH>` with the host's command form (for example
+ 320 `/egm:egm-review <DESIGN_PATH>` in Claude Code and agy CLI, or the skill
+ 321 picker in Codex).
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 05f8984cb6e0
No earlier version was observed for comparison.
skills/egm-drift-report/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Local scripts
05f8984cb6e0 → 113a3afc44e8
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 05f8984cb6e0
No earlier version was observed for comparison.
skills/egm-resolve/SKILL.md
Week of Nov 2, 2026 · +1 / −1 lines
Before Instructions only → After Instructions only
05f8984cb6e0 → 113a3afc44e8
- 98 ### [Issue 1] [`[ReviewerPersona]`] - Severity: [High | Medium | Low]
+ 98 ### [Issue 1] [`[ReviewerPersona]`] - Severity: [Blocker | Major | Nit]
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 05f8984cb6e0
No earlier version was observed for comparison.
skills/egm-review/SKILL.md
Week of Nov 2, 2026 · +33 / −11 lines
Before Instructions only → After Instructions only
05f8984cb6e0 → 113a3afc44e8
- 75 baseline. If omitted, the system defaults to no additional context (but
- 76 always automatically reads files linked or referenced in the design doc).
+ 75 baseline. If omitted, it holds only the linked files that Step 1.3 adds.
- 92 2. Once `TargetFile` is provided, verify if `GoldfishContext` is provided (or
- 93 if the user explicitly stated in their prompt to proceed with no additional
- 94 context). If missing:
+ 91 2. Once `TargetFile` is provided, verify if `GoldfishContext` is provided (an
+ 92 empty list counts as provided, as does the user explicitly stating in their
+ 93 prompt to proceed with no additional context). If missing:
- 97 * Clarify that reviewers **always automatically read** files explicitly
- 98 mentioned or linked in the target design document itself.
+ 96 * Clarify that linked files inside the working directory are added
+ 97 automatically, and that other links and URLs need approval.
+ 101 3. **Linked Files (run later)**: Do not run this during intake. Run it once,
+ 102 after the Step 2 preset is chosen and right before the first stage that
+ 103 takes `GoldfishContext` (any stage but Stage 6), in any flow including
+ 104 `uninterrupted`. Read `TargetFile`, skip anchor-only links (`#...`), drop
+ 105 the `#fragment` from other links, and resolve each relative link against
+ 106 the design document's folder. Add each link whose real path (after
+ 107 following symbolic links) stays inside the working directory to
+ 108 `GoldfishContext`, skipping files that do not exist. If any link resolves
+ 109 outside the working directory or is a URL, list those links in chat as
+ 110 regular text, ask which to include, and end your turn; if no one can
+ 111 answer, as in a headless run, leave them all out and keep going. Add only
+ 112 approved ones and tell the user which were left out. Some reviewers cannot
+ 113 open URLs, so save the raw page of each URL in `GoldfishContext` as a new
+ 114 file in the working directory (or your harness's artifact directory) and
+ 115 pass its absolute path instead. If a page cannot be saved, ask the user for
+ 116 a local copy and end your turn; if no one can answer, as in a headless run,
+ 117 leave it out, tell the user, and keep going. Pass
+ 118 `GoldfishContext` to every stage except Stage 6, which reads the document
+ 119 alone; tell any synthesizer to give these files to each reviewer.
+ 269 * If Step 1.3 has run, apply its rules to links added since then.
- 266 harness's artifact directory, if it has one):
+ 285 harness's artifact directory, if it has one). Pass `GoldfishContext` to
+ 286 every step except Step 6.
+ 323 In both Stage 5 and Stage 8, pass `GoldfishContext`.
- 351 `FeatureRange` with reviewers `[egm-design, egm-structural, egm-style]` and
+ 372 `FeatureRange` with reviewers `[egm-design, egm-structural, egm-style]`,
- 353 "feature-spec-standard"}`.
+ 374 "feature-spec-standard"}`, and `GoldfishContext`.
- 381 "egm-codebase-details": "implementation-readiness-standard"}`.
+ 402 "egm-codebase-details": "implementation-readiness-standard"}`, and
+ 403 `GoldfishContext`.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 05f8984cb6e0
No earlier version was observed for comparison.
skills/egm-review-loop/SKILL.md
Week of Nov 2, 2026 · +11 / −3 lines
Before Instructions only → After Local scripts
05f8984cb6e0 → 113a3afc44e8
- 57 documentation URLs) fed to reviewers to establish their baseline.
+ 57 documentation URLs) fed to reviewers to establish their baseline. An empty
+ 58 list from the caller counts as provided; do not ask for it again. Some
+ 59 reviewers cannot open URLs, so before the first round save the raw page of
+ 60 each URL as a new file in the working directory (or your harness's artifact
+ 61 directory) and pass its absolute path instead. If a page cannot be saved,
+ 62 ask the user for a local copy and end your turn; if no one can answer,
+ 63 as in a headless run, leave it out, tell the user, and keep going.
- 118 conversation. Pass it the Failed Reviewers rule below. Its summary must
- 119 give a status, `completed` or `not run`, for each requested reviewer.
+ 124 conversation. Pass it the Failed Reviewers rule below and
+ 125 `GoldfishContext`, and tell it to give those files to each reviewer.
+ 126 Its summary must give a status, `completed` or `not run`, for each
+ 127 requested reviewer.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 05f8984cb6e0
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit 113a3afc44e8f4f54722d7150d5701f65cc8ef7f
git clone --filter=blob:none --no-checkout https://github.com/google/elephant-goldfish-model.git .hotskills/google-elephant-goldfish-model && git -C .hotskills/google-elephant-goldfish-model checkout --detach 113a3afc44e8f4f54722d7150d5701f65cc8ef7f
# Copy each selected skill directory from .hotskills/google-elephant-goldfish-model into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/google/elephant-goldfish-model.git .hotskills/google-elephant-goldfish-model && git -C .hotskills/google-elephant-goldfish-model checkout --detach 113a3afc44e8f4f54722d7150d5701f65cc8ef7f
# Copy each selected skill directory from .hotskills/google-elephant-goldfish-model into .agents/skills/<skill-name>/12.6kGitHub stars
6.1kstars in 7 days
14skills in this repository
151commits in 30 days
Heat
8.7- Star growth, last 7 daysAhead of 100% of tracked repositories
- Star growth, last 24 hoursAhead of 100% of tracked repositories
- Rank movement, last 7 daysAhead of 99% of tracked repositories
- Commits, last 30 daysAhead of 96% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- egm-bootstrap
distributions/claude/skills/egm-bootstrap - egm-brainstorm
distributions/claude/skills/egm-brainstorm - egm-draft
distributions/claude/skills/egm-draft - egm-drift-report
distributions/claude/skills/egm-drift-report - egm-resolve
distributions/claude/skills/egm-resolve - egm-review
distributions/claude/skills/egm-review - egm-review-loop
distributions/claude/skills/egm-review-loop - egm-bootstrap
skills/egm-bootstrap - egm-brainstorm
skills/egm-brainstorm - egm-draft
skills/egm-draft - egm-drift-report
skills/egm-drift-report - egm-resolve
skills/egm-resolve - egm-review
skills/egm-review - egm-review-loop
skills/egm-review-loop
How it works
egm-bootstrap
When your agent uses it
Bootstrap directory README.md files across a repository subtree.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
5,390 tokensWhen the skill is activated
Reference documents
7,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Delegation
- Inputs
- Execution Constraints (CRITICAL)
- Workflow
- Templates
Files
../../../../.claude-plugin/agents/bootstrap_orchestrator.mddoc921 bytes../../../../.claude-plugin/agents/codebase_details.mddoc666 bytes../../../../.claude-plugin/agents/comprehension.mddoc657 bytes../../../../.claude-plugin/agents/design_critic.mddoc641 bytes../../../../.claude-plugin/agents/implementation_readiness.mddoc673 bytes../../../../.claude-plugin/agents/structural.mddoc639 bytes../../../../.claude-plugin/agents/style.mddoc628 bytes../../../../.claude-plugin/agents/synthesizer.mddoc1,214 bytes../../../../.claude-plugin/agents/zoom_out.mddoc637 bytes../../../../.claude-plugin/icon.pngasset13,264 bytes../../../../.claude-plugin/marketplace.jsonasset218 bytes../../../../.claude-plugin/plugin.jsonasset1,281 bytes../../.claude-plugin/agents/bootstrap_orchestrator.mddoc921 bytes../../.claude-plugin/agents/codebase_details.mddoc666 bytes../../.claude-plugin/agents/comprehension.mddoc657 bytes../../.claude-plugin/agents/design_critic.mddoc641 bytes../../.claude-plugin/agents/implementation_readiness.mddoc673 bytes../../.claude-plugin/agents/structural.mddoc639 bytes../../.claude-plugin/agents/style.mddoc628 bytes../../.claude-plugin/agents/synthesizer.mddoc1,214 bytes../../.claude-plugin/agents/zoom_out.mddoc637 bytes../../.claude-plugin/icon.pngasset13,264 bytes../../.claude-plugin/plugin.jsonasset1,281 bytes../../docs/claude.mddoc10,489 bytes../../docs/codex.mddoc6,812 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesagents/openai.yamlasset198 bytesassets/icon.svgasset601 bytesreferences/templates.mddoc2,064 bytesreferences/worker-return.schema.jsonasset568 bytes
Read SKILL.md
# EGM Peanuts and Hay Bootstrap (`egm-bootstrap`)
When running in Codex or ChatGPT Work, first read [Codex integration](../../docs/codex.md).
In Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}/docs/claude.md` first.
## Overview
This skill automates the creation, correction, formatting, and correctness
verification of Elephant-and-Goldfish Model (EGM) compliant `README.md` files
across a directory tree. It establishes clear architectural contracts
(interfaces, invariants, and side effects) for both human developers and AI
assistants.
* **Peanuts**: Leaf-level Component Package READMEs containing specific fileegm-brainstorm
When your agent uses it
Interactive ideation and brainstorming skill for the Elephant & Goldfish Model (EGM). Helps turn half-baked concepts into structured hypotheses via clarifying questions, review, and iterative refinement. Produces an RFC summary for human review or more detailed design with egm-draft.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
3,469 tokensWhen the skill is activated
Reference documents
3,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Delegation
- Execution Constraints (CRITICAL)
- The Goldfish Brainstorming Lenses
- Execution Workflow
Files
../../docs/claude.mddoc10,489 bytes../../docs/codex.mddoc6,812 bytesSKILL.mdcore14,769 bytesSKILL.mdcore14,769 bytesSKILL.mdcore14,769 bytesagents/openai.yamlasset199 bytesassets/icon.svgasset496 bytes
Read SKILL.md
# EGM Brainstorm: Interactive Multi-Lens Ideation & Refinement
When running in Codex or ChatGPT Work, first read [Codex integration](../../docs/codex.md).
In Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}/docs/claude.md` first.
## Overview
This skill acts as the upstream conversational brainstorming engine for the
Elephant-Goldfish Model (EGM). It turns "half-baked" or raw concepts into
hypotheses by combining **interactive clarifying questions** with an automated
**Goldfish review**. The outcome is an iteratively refined RFC summary
(`concepts_brief.md`) that leads directly into `/egm-draft` or review with
peers.
egm-draft
When your agent uses it
Drafts a design document section-by-section using the concepts brief from egm-brainstorm (or user notes). This is the second step in the Elephant-Goldfish (EGM) feature flow. Use when you are ready to write a design doc after aligning on requirements + solution.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
4,126 tokensWhen the skill is activated
Reference documents
5,012 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Execution Constraints (CRITICAL)
- Inputs
- Execution Workflow
Files
../../docs/claude.mddoc10,489 bytes../../docs/codex.mddoc6,812 bytesSKILL.mdcore17,479 bytesagents/openai.yamlasset198 bytesassets/icon.svgasset545 bytesreferences/design_doc.mddoc5,432 bytes
Read SKILL.md
# Design Drafting (Document Construction)
When running in Codex or ChatGPT Work, first read [Codex integration](../../docs/codex.md).
In Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}/docs/claude.md` first.
This skill guides the user through drafting a technical design document based on
the aligned problem and requirements from the brainstorm phase.
## Execution Constraints (CRITICAL)
1. You **MUST** read and apply the
execution instructions in `resources/execution_instructions.md`.
2. **Artifact-First Delivery (MANDATORY)**: You are **STRICTLY FORBIDDEN** from
presenting large proposals, drafts, summaries, or plans directly in the chategm-drift-report
When your agent uses it
Runs drift detection on all design documents to check for document and code consistency. Produces an actionable report with differences. Use when the user asks to detect drift or check for consistency across all design documents or READMEs in a directory.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
708 tokensWhen the skill is activated
Reference documents
3,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../docs/claude.mddoc10,489 bytes../../docs/codex.mddoc6,812 bytesSKILL.mdcore3,169 bytesSKILL.mdcore3,169 bytesSKILL.mdcore3,169 bytesSKILL.mdcore3,169 bytesagents/openai.yamlasset204 bytesassets/icon.svgasset281 bytes
Read SKILL.md
# Detect Drift In Designs and Code
When running in Codex or ChatGPT Work, first read [Codex integration](../../docs/codex.md).
In Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}/docs/claude.md` first.
When the user asks to detect drift across all designs or a set of READMEs, the
goal is to identify all instances where the codebase has diverged or failed to
implement the specifications described by those designs or READMEs.
1. **Check Input**: Verify a directory containing design documents or READMEs
is provided. If not provided, ask the user to specify the target directory.
2. **List Documents**: List all files in the design directory.
3. **Analyze**: For EACH design document:
egm-resolve
When your agent uses it
The Elephant resolution skill. Ingests flat deficiency reports from concurrent Goldfish reviewers, applies automated fixes for PROPOSE FIX items via UI multiple-choice gates, and presents interactive negotiation/re-sync checkpoints.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
2,027 tokensWhen the skill is activated
Reference documents
3,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Prerequisites & Context Strategy
- Inputs
- Execution Workflow
Files
../../docs/claude.mddoc10,489 bytes../../docs/codex.mddoc6,812 bytesSKILL.mdcore8,541 bytesagents/openai.yamlasset193 bytesassets/icon.svgasset506 bytes
Read SKILL.md
# Goldfish Review: Resolve
When running in Codex or ChatGPT Work, first read [Codex integration](../../docs/codex.md).
In Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}/docs/claude.md` first.
## Overview
This skill instructs the agent on how to operate within the primary Elephant
context window to parse flat deficiency reports from concurrent Goldfish
reviewers. It defends accurate design choices, applies automated textual
repairs, and manages interactive negotiation checkpoints.
## Prerequisites & Context Strategy
egm-review
When your agent uses it
Orchestrates the EGM Goldfish Review Protocol. Used as part of the EGM process to perform design document reviews. Executes five review phases: Initial Zoom Out Review, Comprehension Review, Design Critique, Intermediate Zoom Out Review, and Implementation Readiness.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
5,851 tokensWhen the skill is activated
Reference documents
3,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Delegation
- Execution Constraints (CRITICAL)
- Inputs
- Workflow
- Subflows
Files
../../docs/claude.mddoc10,489 bytes../../docs/codex.mddoc6,812 bytesSKILL.mdcore24,113 bytesagents/openai.yamlasset198 bytesassets/icon.svgasset530 bytes
Read SKILL.md
# Review, Validation & Automated Remediation
When running in Codex or ChatGPT Work, first read [Codex integration](../../docs/codex.md).
In Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}/docs/claude.md` first.
Reviews and validates a design document through specialized reviewer personas.
## Delegation
A Goldfish runs in a fresh context with no conversation history. Spawn each
subagent with your harness's subagent tool (Antigravity: `invoke_subagent`; Claude Code: `Agent`; Codex: `spawn_agent`). Each subagent is defined in `agents/<file>.md`, and its
frontmatter `name` (for example `egm-zoom-out`) is the subagent type to request
where your harness registers named subagents. Otherwise spawn a general-purpose
subagent and tell it to read that persona file first. Pass the prompt verbatimegm-review-loop
When your agent uses it
Executes the Antagonistic-Review process from the Elephant-Goldfish Model (EGM) via an automated multi-agent review loop to audit documents against qualitative standards and structural templates, and automatically apply approved fixes. Use when reviewing design docs, READMEs, feature specifications, implementation plans, or verifying document completeness and tone.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
2,410 tokensWhen the skill is activated
Reference documents
3,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Delegation
- Inputs
- Path & Standard Resolution Logic
- Execution Workflow
Files
../../docs/claude.mddoc10,489 bytes../../docs/codex.mddoc6,812 bytesSKILL.mdcore10,325 bytesSKILL.mdcore10,325 bytesagents/openai.yamlasset204 bytesassets/icon.svgasset544 bytes
Read SKILL.md
# Goldfish Review: Loop (Orchestration Driver)
When running in Codex or ChatGPT Work, first read [Codex integration](../../docs/codex.md).
In Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}/docs/claude.md` first.
## Overview
This skill acts as the central orchestration engine driving the multi-agent
review loop. It coordinates two distinct agent memory models:
* **The Goldfish (Adversarial Auditors)**: Subagents spawned in isolated,
fresh context windows to catch unstated assumptions without historical bias.
* **The Elephant (Persistent Resolver)**: The primary agent context holding
institutional knowledge to evaluate findings and apply approved repairs.egm-bootstrap
When your agent uses it
Bootstrap directory README.md files across a repository subtree.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
5,390 tokensWhen the skill is activated
Reference documents
4,499 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Delegation
- Inputs
- Execution Constraints (CRITICAL)
- Workflow
- Templates
Files
../../docs/claude.mddoc10,489 bytes../../docs/codex.mddoc6,812 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesSKILL.mdcore23,764 bytesTEST.mddoc863 bytesagents/openai.yamlasset198 bytesassets/icon.svgasset601 bytesreferences/templates.mddoc2,064 bytesreferences/worker-return.schema.jsonasset568 bytestest_scenarios.yamlasset3,835 bytes
Read SKILL.md
# EGM Peanuts and Hay Bootstrap (`egm-bootstrap`)
When running in Codex or ChatGPT Work, first read [Codex integration](../../docs/codex.md).
In Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}/docs/claude.md` first.
## Overview
This skill automates the creation, correction, formatting, and correctness
verification of Elephant-and-Goldfish Model (EGM) compliant `README.md` files
across a directory tree. It establishes clear architectural contracts
(interfaces, invariants, and side effects) for both human developers and AI
assistants.
* **Peanuts**: Leaf-level Component Package READMEs containing specific fileegm-brainstorm
When your agent uses it
Interactive ideation and brainstorming skill for the Elephant & Goldfish Model (EGM). Helps turn half-baked concepts into structured hypotheses via clarifying questions, review, and iterative refinement. Produces an RFC summary for human review or more detailed design with egm-draft.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
3,469 tokensWhen the skill is activated
Reference documents
4,069 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Delegation
- Execution Constraints (CRITICAL)
- The Goldfish Brainstorming Lenses
- Execution Workflow
Files
../../docs/claude.mddoc10,489 bytes../../docs/codex.mddoc6,812 bytesSKILL.mdcore14,769 bytesSKILL.mdcore14,769 bytesSKILL.mdcore14,769 bytesTEST.mddoc946 bytesagents/openai.yamlasset199 bytesassets/icon.svgasset496 bytestest_scenarios.yamlasset7,170 bytes
Read SKILL.md
# EGM Brainstorm: Interactive Multi-Lens Ideation & Refinement
When running in Codex or ChatGPT Work, first read [Codex integration](../../docs/codex.md).
In Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}/docs/claude.md` first.
## Overview
This skill acts as the upstream conversational brainstorming engine for the
Elephant-Goldfish Model (EGM). It turns "half-baked" or raw concepts into
hypotheses by combining **interactive clarifying questions** with an automated
**Goldfish review**. The outcome is an iteratively refined RFC summary
(`concepts_brief.md`) that leads directly into `/egm-draft` or review with
peers.
egm-draft
When your agent uses it
Drafts a design document section-by-section using the concepts brief from egm-brainstorm (or user notes). This is the second step in the Elephant-Goldfish (EGM) feature flow. Use when you are ready to write a design doc after aligning on requirements + solution.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
4,126 tokensWhen the skill is activated
Reference documents
5,153 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Execution Constraints (CRITICAL)
- Inputs
- Execution Workflow
Files
../../docs/claude.mddoc10,489 bytes../../docs/codex.mddoc6,812 bytesSKILL.mdcore17,479 bytesTEST.mddoc595 bytesagents/openai.yamlasset198 bytesassets/icon.svgasset545 bytesreferences/design_doc.mddoc5,432 bytestest_scenarios.yamlasset8,592 bytes
Read SKILL.md
# Design Drafting (Document Construction)
When running in Codex or ChatGPT Work, first read [Codex integration](../../docs/codex.md).
In Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}/docs/claude.md` first.
This skill guides the user through drafting a technical design document based on
the aligned problem and requirements from the brainstorm phase.
## Execution Constraints (CRITICAL)
1. You **MUST** read and apply the
execution instructions in `resources/execution_instructions.md`.
2. **Artifact-First Delivery (MANDATORY)**: You are **STRICTLY FORBIDDEN** from
presenting large proposals, drafts, summaries, or plans directly in the chategm-drift-report
When your agent uses it
Runs drift detection on all design documents to check for document and code consistency. Produces an actionable report with differences. Use when the user asks to detect drift or check for consistency across all design documents or READMEs in a directory.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
708 tokensWhen the skill is activated
Reference documents
3,875 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../docs/claude.mddoc10,489 bytes../../docs/codex.mddoc6,812 bytesSKILL.mdcore3,169 bytesSKILL.mdcore3,169 bytesSKILL.mdcore3,169 bytesSKILL.mdcore3,169 bytesTEST.mddoc130 bytesagents/openai.yamlasset204 bytesassets/icon.svgasset281 bytestest_scenarios.yamlasset1,327 bytes
Read SKILL.md
# Detect Drift In Designs and Code
When running in Codex or ChatGPT Work, first read [Codex integration](../../docs/codex.md).
In Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}/docs/claude.md` first.
When the user asks to detect drift across all designs or a set of READMEs, the
goal is to identify all instances where the codebase has diverged or failed to
implement the specifications described by those designs or READMEs.
1. **Check Input**: Verify a directory containing design documents or READMEs
is provided. If not provided, ask the user to specify the target directory.
2. **List Documents**: List all files in the design directory.
3. **Analyze**: For EACH design document:
egm-resolve
When your agent uses it
The Elephant resolution skill. Ingests flat deficiency reports from concurrent Goldfish reviewers, applies automated fixes for PROPOSE FIX items via UI multiple-choice gates, and presents interactive negotiation/re-sync checkpoints.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
2,027 tokensWhen the skill is activated
Reference documents
4,053 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Prerequisites & Context Strategy
- Inputs
- Execution Workflow
Files
../../docs/claude.mddoc10,489 bytes../../docs/codex.mddoc6,812 bytesSKILL.mdcore8,541 bytesTEST.mddoc871 bytesagents/openai.yamlasset193 bytesassets/icon.svgasset506 bytestest_scenarios.yamlasset1,941 bytes
Read SKILL.md
# Goldfish Review: Resolve
When running in Codex or ChatGPT Work, first read [Codex integration](../../docs/codex.md).
In Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}/docs/claude.md` first.
## Overview
This skill instructs the agent on how to operate within the primary Elephant
context window to parse flat deficiency reports from concurrent Goldfish
reviewers. It defends accurate design choices, applies automated textual
repairs, and manages interactive negotiation checkpoints.
## Prerequisites & Context Strategy
egm-review
When your agent uses it
Orchestrates the EGM Goldfish Review Protocol. Used as part of the EGM process to perform design document reviews. Executes five review phases: Initial Zoom Out Review, Comprehension Review, Design Critique, Intermediate Zoom Out Review, and Implementation Readiness.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
5,851 tokensWhen the skill is activated
Reference documents
4,072 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Delegation
- Execution Constraints (CRITICAL)
- Inputs
- Workflow
- Subflows
Files
../../docs/claude.mddoc10,489 bytes../../docs/codex.mddoc6,812 bytesSKILL.mdcore24,113 bytesTEST.mddoc996 bytesagents/openai.yamlasset198 bytesassets/icon.svgasset530 bytestest_scenarios.yamlasset9,780 bytes
Read SKILL.md
# Review, Validation & Automated Remediation
When running in Codex or ChatGPT Work, first read [Codex integration](../../docs/codex.md).
In Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}/docs/claude.md` first.
Reviews and validates a design document through specialized reviewer personas.
## Delegation
A Goldfish runs in a fresh context with no conversation history. Spawn each
subagent with your harness's subagent tool (Antigravity: `invoke_subagent`; Claude Code: `Agent`; Codex: `spawn_agent`). Each subagent is defined in `agents/<file>.md`, and its
frontmatter `name` (for example `egm-zoom-out`) is the subagent type to request
where your harness registers named subagents. Otherwise spawn a general-purpose
subagent and tell it to read that persona file first. Pass the prompt verbatimegm-review-loop
When your agent uses it
Executes the Antagonistic-Review process from the Elephant-Goldfish Model (EGM) via an automated multi-agent review loop to audit documents against qualitative standards and structural templates, and automatically apply approved fixes. Use when reviewing design docs, READMEs, feature specifications, implementation plans, or verifying document completeness and tone.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
2,410 tokensWhen the skill is activated
Reference documents
4,121 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Delegation
- Inputs
- Path & Standard Resolution Logic
- Execution Workflow
Files
../../docs/claude.mddoc10,489 bytes../../docs/codex.mddoc6,812 bytesSKILL.mdcore10,325 bytesSKILL.mdcore10,325 bytesTEST.mddoc1,180 bytesagents/openai.yamlasset204 bytesassets/icon.svgasset544 bytestest_scenarios.yamlasset5,179 bytes
Read SKILL.md
# Goldfish Review: Loop (Orchestration Driver)
When running in Codex or ChatGPT Work, first read [Codex integration](../../docs/codex.md).
In Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}/docs/claude.md` first.
## Overview
This skill acts as the central orchestration engine driving the multi-agent
review loop. It coordinates two distinct agent memory models:
* **The Goldfish (Adversarial Auditors)**: Subagents spawned in isolated,
fresh context windows to catch unstated assumptions without historical bias.
* **The Elephant (Persistent Resolver)**: The primary agent context holding
institutional knowledge to evaluate findings and apply approved repairs.Skills included
- egm-bootstrap
- egm-brainstorm
- egm-draft
- egm-drift-report
- egm-resolve
- egm-review
- egm-review-loop
- egm-bootstrap
- egm-brainstorm
- egm-draft
- egm-drift-report
- egm-resolve
- egm-review
- egm-review-loop
Repository facts
- License
- Apache-2.0
- Created
- Sep 13, 2026
- Last pushed
- Nov 5, 2026
- Forks
- 902
- Open issues
- 45
- Project activity
- Active
Rank over the last 12 weeks
Now #126 · best #126 · up 778 in 30 days
- #188 on Oct 31
- #162 on Nov 1
- #143 on Nov 2
- #136 on Nov 3
- #131 on Nov 4
- #126 since Nov 5
8 earlier periods
- #904 on Sep 13
- #996 on Oct 21
- #961 on Oct 22
- #974 on Oct 23
- #909 on Oct 24
- #274 on Oct 28
- #242 on Oct 29
- #213 on Oct 30
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 32 notes
distributions/claude/skills/egm-bootstrap/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistributions/claude/skills/egm-bootstrap/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistributions/claude/skills/egm-bootstrap/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistributions/claude/skills/egm-bootstrap/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistributions/claude/skills/egm-bootstrap/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistributions/claude/skills/egm-bootstrap/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistributions/claude/skills/egm-bootstrap/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistributions/claude/skills/egm-bootstrap/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistributions/claude/skills/egm-bootstrap/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistributions/claude/skills/egm-bootstrap/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistributions/claude/skills/egm-brainstorm/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistributions/claude/skills/egm-brainstorm/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistributions/claude/skills/egm-drift-report/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistributions/claude/skills/egm-drift-report/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistributions/claude/skills/egm-drift-report/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistributions/claude/skills/egm-review-loop/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/egm-bootstrap/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/egm-bootstrap/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/egm-bootstrap/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/egm-bootstrap/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 207 network referencesin 27 files: distributions/claude/docs/codex.md:72 docs/codex.md:72 distributions/claude/docs/claude.md:185 and 24 more
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 207 signals by file
.claude-plugin/plugin.json
- Network accessline 7
"name": "Google" }, "homepage": "https://egm.dev", - Network accessline 8
}, "homepage": "https://egm.dev", "repository": "https://github.com/google/elephant-goldfish-model", - Network accessline 9
"homepage": "https://egm.dev", - Network accessline 10
"repository": "https://github.com/google/elephant-goldfish-model", - Network accessline 12
"keywords": ["spec-driven-development", "design-documents", "design-review"], "icon": "./.claude-plugin/icon.png", "documentationUrl": "https://github.com/google/elephant-goldfish-model/blob/main/docs/claude.md", - Network accessline 13
"icon": "./.claude-plugin/icon.png", "documentationUrl": "https://github.com/google/elephant-goldfish-model/blob/main/docs/claude.md", "supportUrl": "https://github.com/google/elephant-goldfish-model/issues", - Network accessline 14
"documentationUrl": "https://github.com/google/elephant-goldfish-model/blob/main/docs/claude.md", - Network accessline 15
"supportUrl": "https://github.com/google/elephant-goldfish-model/issues", - Network accessline 16
"privacyPolicyUrl": "https://github.com/google/elephant-goldfish-model/blob/main/docs/privacy.md", - Network accessline 17
"termsOfServiceUrl": "https://github.com/google/elephant-goldfish-model/blob/main/LICENSE",
distributions/claude/.claude-plugin/plugin.json
- Network accessline 7
"name": "Google" }, "homepage": "https://egm.dev", - Network accessline 8
}, "homepage": "https://egm.dev", "repository": "https://github.com/google/elephant-goldfish-model", - Network accessline 9
"homepage": "https://egm.dev", - Network accessline 10
"repository": "https://github.com/google/elephant-goldfish-model", - Network accessline 12
"keywords": ["spec-driven-development", "design-documents", "design-review"], "icon": "./.claude-plugin/icon.png", "documentationUrl": "https://github.com/google/elephant-goldfish-model/blob/main/docs/claude.md", - Network accessline 13
"icon": "./.claude-plugin/icon.png", "documentationUrl": "https://github.com/google/elephant-goldfish-model/blob/main/docs/claude.md", "supportUrl": "https://github.com/google/elephant-goldfish-model/issues", - Network accessline 14
"documentationUrl": "https://github.com/google/elephant-goldfish-model/blob/main/docs/claude.md", - Network accessline 15
"supportUrl": "https://github.com/google/elephant-goldfish-model/issues", - Network accessline 16
"privacyPolicyUrl": "https://github.com/google/elephant-goldfish-model/blob/main/docs/privacy.md", - Network accessline 17
"termsOfServiceUrl": "https://github.com/google/elephant-goldfish-model/blob/main/LICENSE",
distributions/claude/docs/claude.md
- Network accessline 185
References: [plugin paths](https://code.claude.com/docs/en/plugins-reference), - Network accessline 185
References: [plugin paths](https://code.claude.com/docs/en/plugins-reference), - Network accessline 185
References: [plugin paths](https://code.claude.com/docs/en/plugins-reference), - Network accessline 185
References: [plugin paths](https://code.claude.com/docs/en/plugins-reference), - Network accessline 185
References: [plugin paths](https://code.claude.com/docs/en/plugins-reference), - Network accessline 185
References: [plugin paths](https://code.claude.com/docs/en/plugins-reference), - Network accessline 185
References: [plugin paths](https://code.claude.com/docs/en/plugins-reference), - Network accessline 186
[skill invocation](https://code.claude.com/docs/en/skills), and - Network accessline 186
[skill invocation](https://code.claude.com/docs/en/skills), and - Network accessline 186
[skill invocation](https://code.claude.com/docs/en/skills), and - Network accessline 186
[skill invocation](https://code.claude.com/docs/en/skills), and - Network accessline 186
[skill invocation](https://code.claude.com/docs/en/skills), and - Network accessline 186
[skill invocation](https://code.claude.com/docs/en/skills), and - Network accessline 186
[skill invocation](https://code.claude.com/docs/en/skills), and - Network accessline 187
[subagent context and tools](https://code.claude.com/docs/en/sub-agents). - Network accessline 187
[subagent context and tools](https://code.claude.com/docs/en/sub-agents). - Network accessline 187
[subagent context and tools](https://code.claude.com/docs/en/sub-agents). - Network accessline 187
[subagent context and tools](https://code.claude.com/docs/en/sub-agents). - Network accessline 187
[subagent context and tools](https://code.claude.com/docs/en/sub-agents). - Network accessline 187
[subagent context and tools](https://code.claude.com/docs/en/sub-agents). - Network accessline 187
[subagent context and tools](https://code.claude.com/docs/en/sub-agents).
distributions/claude/docs/codex.md
- Network accessline 72
The `fork_context: false` and `fork_turns: "none"` options concern parent conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 72
The `fork_context: false` and `fork_turns: "none"` options concern parent conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 72
The `fork_context: false` and `fork_turns: "none"` options concern parent conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 72
The `fork_context: false` and `fork_turns: "none"` options concern parent conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 72
The `fork_context: false` and `fork_turns: "none"` options concern parent conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 72
The `fork_context: false` and `fork_turns: "none"` options concern parent conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 72
The `fork_context: false` and `fork_turns: "none"` options concern parent conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 73
conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) reports that Codex CLI 0.166.0 injected project and user `AGENTS.md` files - Network accessline 73
conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) reports that Codex CLI 0.166.0 injected project and user `AGENTS.md` files - Network accessline 73
conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) reports that Codex CLI 0.166.0 injected project and user `AGENTS.md` files - Network accessline 73
conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) reports that Codex CLI 0.166.0 injected project and user `AGENTS.md` files - Network accessline 73
conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) reports that Codex CLI 0.166.0 injected project and user `AGENTS.md` files - Network accessline 73
conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) reports that Codex CLI 0.166.0 injected project and user `AGENTS.md` files - Network accessline 73
conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) reports that Codex CLI 0.166.0 injected project and user `AGENTS.md` files - Network accessline 74
files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 74
files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 74
files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 74
files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 74
files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 74
files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 74
files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 94
Run the offline packaging checks with `pytest tests/unit`. The opt-in native workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 94
Run the offline packaging checks with `pytest tests/unit`. The opt-in native workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 94
Run the offline packaging checks with `pytest tests/unit`. The opt-in native workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 94
Run the offline packaging checks with `pytest tests/unit`. The opt-in native workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 94
Run the offline packaging checks with `pytest tests/unit`. The opt-in native workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 94
Run the offline packaging checks with `pytest tests/unit`. The opt-in native workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 94
Run the offline packaging checks with `pytest tests/unit`. The opt-in native workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 95
workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 95
workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 95
workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 95
workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 95
workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 95
workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 95
workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 119
Enterprise, Business, and Edu workspaces can import the plugin via Admin > Plugins > Add > Import marketplace. Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 119
Enterprise, Business, and Edu workspaces can import the plugin via Admin > Plugins > Add > Import marketplace. Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 119
Enterprise, Business, and Edu workspaces can import the plugin via Admin > Plugins > Add > Import marketplace. Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 119
Enterprise, Business, and Edu workspaces can import the plugin via Admin > Plugins > Add > Import marketplace. Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 119
Enterprise, Business, and Edu workspaces can import the plugin via Admin > Plugins > Add > Import marketplace. Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 119
Enterprise, Business, and Edu workspaces can import the plugin via Admin > Plugins > Add > Import marketplace. Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 119
Enterprise, Business, and Edu workspaces can import the plugin via Admin > Plugins > Add > Import marketplace. Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 120
Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 120
Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 120
Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 120
Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 120
Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 120
Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 120
Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`.
distributions/claude/skills/egm-bootstrap/assets/icon.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"><title>Bootstrap</title><g transform="matrix(1.05 0 0 1.05 -0.600000 -0.600000)"><path fill="#1b6ef3" d="M9.2 5.6A2.8 2.8 0 0 1 14.8 5.6V8.2A1 1 0 0 0 15.8 9
distributions/claude/skills/egm-brainstorm/assets/icon.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"><title>Brainstorm</title><g transform="matrix(1.03 0 0 1.03 -0.360000 -0.360000)"><g transform="translate(0.404494 0.307865) scale(0.966292)"><path fill="#1b
distributions/claude/skills/egm-draft/assets/icon.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"><title>Draft</title><g transform="matrix(0.98 0 0 0.98 0.240000 0.240000)"><g transform="translate(-0.919547 -2.255662) scale(1.132300)"><path fill="#1b6ef3"
distributions/claude/skills/egm-drift-report/assets/icon.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"><title>Drift report</title><g transform="translate(-0.333333 -0.333333) scale(1.027778)"><path fill="#e86e00" d="M12 3A8 7 0 0 0 12 17Z"/><path fill="#ff8d41
distributions/claude/skills/egm-resolve/assets/icon.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"><title>Resolve</title><g transform="matrix(0.985 0 0 0.985 0.180000 0.180000)"><g transform="translate(1.393902 0.623415) scale(0.951220)"><path fill="#1b6ef
distributions/claude/skills/egm-review-loop/assets/icon.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"><title>Review loop</title><g transform="matrix(1 0 0 1 0.000000 0.350000)"><g transform="translate(0.652062 0.089433) scale(0.953608)"><path fill="none" stro
distributions/claude/skills/egm-review/assets/icon.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"><title>Review</title><g transform="matrix(1 0 0 1 0.250000 0.250000)"><g transform="translate(-0.673383 -0.522269) scale(1.007423)"><path fill="#e86e00" d="M
docs/claude.md
- Network accessline 185
References: [plugin paths](https://code.claude.com/docs/en/plugins-reference), - Network accessline 185
References: [plugin paths](https://code.claude.com/docs/en/plugins-reference), - Network accessline 185
References: [plugin paths](https://code.claude.com/docs/en/plugins-reference), - Network accessline 185
References: [plugin paths](https://code.claude.com/docs/en/plugins-reference), - Network accessline 185
References: [plugin paths](https://code.claude.com/docs/en/plugins-reference), - Network accessline 185
References: [plugin paths](https://code.claude.com/docs/en/plugins-reference), - Network accessline 185
References: [plugin paths](https://code.claude.com/docs/en/plugins-reference), - Network accessline 186
[skill invocation](https://code.claude.com/docs/en/skills), and - Network accessline 186
[skill invocation](https://code.claude.com/docs/en/skills), and - Network accessline 186
[skill invocation](https://code.claude.com/docs/en/skills), and - Network accessline 186
[skill invocation](https://code.claude.com/docs/en/skills), and - Network accessline 186
[skill invocation](https://code.claude.com/docs/en/skills), and - Network accessline 186
[skill invocation](https://code.claude.com/docs/en/skills), and - Network accessline 186
[skill invocation](https://code.claude.com/docs/en/skills), and - Network accessline 187
[subagent context and tools](https://code.claude.com/docs/en/sub-agents). - Network accessline 187
[subagent context and tools](https://code.claude.com/docs/en/sub-agents). - Network accessline 187
[subagent context and tools](https://code.claude.com/docs/en/sub-agents). - Network accessline 187
[subagent context and tools](https://code.claude.com/docs/en/sub-agents). - Network accessline 187
[subagent context and tools](https://code.claude.com/docs/en/sub-agents). - Network accessline 187
[subagent context and tools](https://code.claude.com/docs/en/sub-agents). - Network accessline 187
[subagent context and tools](https://code.claude.com/docs/en/sub-agents).
docs/codex.md
- Network accessline 72
The `fork_context: false` and `fork_turns: "none"` options concern parent conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 72
The `fork_context: false` and `fork_turns: "none"` options concern parent conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 72
The `fork_context: false` and `fork_turns: "none"` options concern parent conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 72
The `fork_context: false` and `fork_turns: "none"` options concern parent conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 72
The `fork_context: false` and `fork_turns: "none"` options concern parent conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 72
The `fork_context: false` and `fork_turns: "none"` options concern parent conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 72
The `fork_context: false` and `fork_turns: "none"` options concern parent conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 73
conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) reports that Codex CLI 0.166.0 injected project and user `AGENTS.md` files - Network accessline 73
conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) reports that Codex CLI 0.166.0 injected project and user `AGENTS.md` files - Network accessline 73
conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) reports that Codex CLI 0.166.0 injected project and user `AGENTS.md` files - Network accessline 73
conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) reports that Codex CLI 0.166.0 injected project and user `AGENTS.md` files - Network accessline 73
conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) reports that Codex CLI 0.166.0 injected project and user `AGENTS.md` files - Network accessline 73
conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) reports that Codex CLI 0.166.0 injected project and user `AGENTS.md` files - Network accessline 73
conversation turns. They do not prove that Codex excludes host instruction files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) reports that Codex CLI 0.166.0 injected project and user `AGENTS.md` files - Network accessline 74
files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 74
files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 74
files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 74
files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 74
files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 74
files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 74
files. Issue [#237](https://github.com/google/elephant-goldfish-model/issues/237) - Network accessline 94
Run the offline packaging checks with `pytest tests/unit`. The opt-in native workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 94
Run the offline packaging checks with `pytest tests/unit`. The opt-in native workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 94
Run the offline packaging checks with `pytest tests/unit`. The opt-in native workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 94
Run the offline packaging checks with `pytest tests/unit`. The opt-in native workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 94
Run the offline packaging checks with `pytest tests/unit`. The opt-in native workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 94
Run the offline packaging checks with `pytest tests/unit`. The opt-in native workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 94
Run the offline packaging checks with `pytest tests/unit`. The opt-in native workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 95
workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 95
workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 95
workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 95
workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 95
workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 95
workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 95
workflow tests are documented in [TESTING.md](https://github.com/google/elephant-goldfish-model/blob/main/TESTING.md). They require - Network accessline 119
Enterprise, Business, and Edu workspaces can import the plugin via Admin > Plugins > Add > Import marketplace. Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 119
Enterprise, Business, and Edu workspaces can import the plugin via Admin > Plugins > Add > Import marketplace. Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 119
Enterprise, Business, and Edu workspaces can import the plugin via Admin > Plugins > Add > Import marketplace. Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 119
Enterprise, Business, and Edu workspaces can import the plugin via Admin > Plugins > Add > Import marketplace. Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 119
Enterprise, Business, and Edu workspaces can import the plugin via Admin > Plugins > Add > Import marketplace. Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 119
Enterprise, Business, and Edu workspaces can import the plugin via Admin > Plugins > Add > Import marketplace. Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 119
Enterprise, Business, and Edu workspaces can import the plugin via Admin > Plugins > Add > Import marketplace. Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 120
Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 120
Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 120
Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 120
Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 120
Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 120
Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`. - Network accessline 120
Set the repository URL to `https://github.com/google/elephant-goldfish-model` and marketplace path to `.agents/plugins`.
skills/egm-bootstrap/assets/icon.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"><title>Bootstrap</title><g transform="matrix(1.05 0 0 1.05 -0.600000 -0.600000)"><path fill="#1b6ef3" d="M9.2 5.6A2.8 2.8 0 0 1 14.8 5.6V8.2A1 1 0 0 0 15.8 9
skills/egm-bootstrap/test_scenarios.yaml
skills/egm-brainstorm/assets/icon.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"><title>Brainstorm</title><g transform="matrix(1.03 0 0 1.03 -0.360000 -0.360000)"><g transform="translate(0.404494 0.307865) scale(0.966292)"><path fill="#1b
skills/egm-brainstorm/test_scenarios.yaml
skills/egm-draft/assets/icon.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"><title>Draft</title><g transform="matrix(0.98 0 0 0.98 0.240000 0.240000)"><g transform="translate(-0.919547 -2.255662) scale(1.132300)"><path fill="#1b6ef3"
skills/egm-draft/test_scenarios.yaml
skills/egm-drift-report/assets/icon.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"><title>Drift report</title><g transform="translate(-0.333333 -0.333333) scale(1.027778)"><path fill="#e86e00" d="M12 3A8 7 0 0 0 12 17Z"/><path fill="#ff8d41
skills/egm-drift-report/test_scenarios.yaml
skills/egm-resolve/assets/icon.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"><title>Resolve</title><g transform="matrix(0.985 0 0 0.985 0.180000 0.180000)"><g transform="translate(1.393902 0.623415) scale(0.951220)"><path fill="#1b6ef
skills/egm-resolve/test_scenarios.yaml
skills/egm-review-loop/assets/icon.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"><title>Review loop</title><g transform="matrix(1 0 0 1 0.000000 0.350000)"><g transform="translate(0.652062 0.089433) scale(0.953608)"><path fill="none" stro
skills/egm-review-loop/test_scenarios.yaml
- Network accessline 5
# You may obtain a copy of the License at # # https://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # https://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# https://www.apache.org/licenses/LICENSE-2.0 - Network accessline 59
skill_file: "skills/egm-review-loop/SKILL.md" turns: - user_input: "Run the review loop on docs/design.md, full file, with reviewers design_critic and structural, both on feature-spec-standard, and GoldfishContext [src/cache.py, h - Network accessline 60
turns: - user_input: "Run the review loop on docs/design.md, full file, with reviewers design_critic and structural, both on feature-spec-standard, and GoldfishContext [src/cache.py, https://redis.io/docs/latest/develop/use/keyspace/] - Network accessline 61
- user_input: "Run the review loop on docs/design.md, full file, with reviewers design_critic and structural, both on feature-spec-standard, and GoldfishContext [src/cache.py, https://redis.io/docs/latest/develop/use/keyspace/]. I confirm t - Network accessline 77
skill_file: "skills/egm-review-loop/SKILL.md" turns: - user_input: "Run the review loop on docs/design.md, full file, with reviewers design_critic and structural, both on feature-spec-standard, and GoldfishContext [src/cache.py, h - Network accessline 78
turns: - user_input: "Run the review loop on docs/design.md, full file, with reviewers design_critic and structural, both on feature-spec-standard, and GoldfishContext [src/cache.py, https://redis.io/docs/latest/develop/use/keyspace/] - Network accessline 79
- user_input: "Run the review loop on docs/design.md, full file, with reviewers design_critic and structural, both on feature-spec-standard, and GoldfishContext [src/cache.py, https://redis.io/docs/latest/develop/use/keyspace/]. Network acc
skills/egm-review/assets/icon.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"><title>Review</title><g transform="matrix(1 0 0 1 0.250000 0.250000)"><g transform="translate(-0.673383 -0.522269) scale(1.007423)"><path fill="#e86e00" d="M
skills/egm-review/test_scenarios.yaml
- Network accessline 5
# You may obtain a copy of the License at # # https://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # https://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# https://www.apache.org/licenses/LICENSE-2.0 - Network accessline 131
skill_file: "skills/egm-review/SKILL.md" turns: - user_input: "Run EGM Review on docs/design.md with Step: uninterrupted and no additional context. The doc links to ./api.md, /etc/hosts, ../../other-repo/notes.md, and https://exam - Network accessline 132
turns: - user_input: "Run EGM Review on docs/design.md with Step: uninterrupted and no additional context. The doc links to ./api.md, /etc/hosts, ../../other-repo/notes.md, and https://example.com/spec." assertions: - Network accessline 133
- user_input: "Run EGM Review on docs/design.md with Step: uninterrupted and no additional context. The doc links to ./api.md, /etc/hosts, ../../other-repo/notes.md, and https://example.com/spec." - Network accessline 160
skill_file: "skills/egm-review/SKILL.md" turns: - user_input: "Run EGM Review on docs/design.md with Step: 5 and GoldfishContext [https://redis.io/docs/latest/develop/use/keyspace/]. The doc cites no other sources." - Network accessline 161
turns: - user_input: "Run EGM Review on docs/design.md with Step: 5 and GoldfishContext [https://redis.io/docs/latest/develop/use/keyspace/]. The doc cites no other sources." assertions: - Network accessline 162
- user_input: "Run EGM Review on docs/design.md with Step: 5 and GoldfishContext [https://redis.io/docs/latest/develop/use/keyspace/]. The doc cites no other sources."
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 140 facts
- Network access in prose of documentationdistributions/claude/docs/claude.md:185Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:185Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:185Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:185Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:185Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:185Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:185Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:186Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:186Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:186Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:186Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:186Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:186Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:186Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:187Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:187Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:187Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:187Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:187Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:187Low confidence
- Network access in prose of documentationdistributions/claude/docs/claude.md:187Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:72Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:72Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:72Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:72Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:72Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:72Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:72Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:73Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:73Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:73Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:73Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:73Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:73Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:73Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:74Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:74Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:74Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:74Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:74Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:74Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:74Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:94Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:94Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:94Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:94Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:94Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:94Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:94Low confidence
- Network access in prose of documentationdistributions/claude/docs/codex.md:95Low confidence
and 90 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md distributions/claude/skills/egm-bootstrap/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md distributions/claude/skills/egm-bootstrap/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md distributions/claude/skills/egm-bootstrap/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md distributions/claude/skills/egm-bootstrap/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/google-elephant-goldfish-model/)