Not in the top 1,000 by GitHub stars
tzachbon/smart-ralph
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow.
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
plugins/ralph-speckit/skills/communication-style/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-speckit/skills/delegation-principle/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-speckit/skills/smart-ralph/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-speckit/skills/speckit-workflow/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum-codex/skills/interview-framework-codex/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum-codex/skills/ralph-specum/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum-codex/skills/ralph-specum-cancel/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum-codex/skills/ralph-specum-design/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum-codex/skills/ralph-specum-feedback/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum-codex/skills/ralph-specum-help/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum-codex/skills/ralph-specum-implement/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum-codex/skills/ralph-specum-index/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum-codex/skills/ralph-specum-prototype/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum-codex/skills/ralph-specum-refactor/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum-codex/skills/ralph-specum-requirements/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum-codex/skills/ralph-specum-research/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum-codex/skills/ralph-specum-start/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum-codex/skills/ralph-specum-status/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum-codex/skills/ralph-specum-switch/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum-codex/skills/ralph-specum-tasks/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum-codex/skills/ralph-specum-triage/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum/skills/communication-style/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum/skills/interview-framework/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum/skills/reality-verification/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum/skills/smart-ralph/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
plugins/ralph-specum/skills/spec-workflow/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ac7251a0a056
No earlier version was observed for comparison.
Verified commit ac7251a0a056b51435192443775f3cbbc4675cba
git clone --filter=blob:none --no-checkout https://github.com/tzachbon/smart-ralph.git .hotskills/tzachbon-smart-ralph && git -C .hotskills/tzachbon-smart-ralph checkout --detach ac7251a0a056b51435192443775f3cbbc4675cba
# Copy each selected skill directory from .hotskills/tzachbon-smart-ralph into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/tzachbon/smart-ralph.git .hotskills/tzachbon-smart-ralph && git -C .hotskills/tzachbon-smart-ralph checkout --detach ac7251a0a056b51435192443775f3cbbc4675cba
# Copy each selected skill directory from .hotskills/tzachbon-smart-ralph into .agents/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/tzachbon/smart-ralph.git .hotskills/tzachbon-smart-ralph && git -C .hotskills/tzachbon-smart-ralph checkout --detach ac7251a0a056b51435192443775f3cbbc4675cba
# Copy each selected skill directory from .hotskills/tzachbon-smart-ralph into .cursor/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/tzachbon/smart-ralph.git .hotskills/tzachbon-smart-ralph && git -C .hotskills/tzachbon-smart-ralph checkout --detach ac7251a0a056b51435192443775f3cbbc4675cba
# Copy each selected skill directory from .hotskills/tzachbon-smart-ralph into .gemini/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/tzachbon/smart-ralph.git .hotskills/tzachbon-smart-ralph && git -C .hotskills/tzachbon-smart-ralph checkout --detach ac7251a0a056b51435192443775f3cbbc4675cba
# Copy each selected skill directory from .hotskills/tzachbon-smart-ralph into .github/skills/<skill-name>/Heat
2.4- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- communication-style
plugins/ralph-speckit/skills/communication-style - delegation-principle
plugins/ralph-speckit/skills/delegation-principle - smart-ralph
plugins/ralph-speckit/skills/smart-ralph - speckit-workflow
plugins/ralph-speckit/skills/speckit-workflow - interview-framework-codex
plugins/ralph-specum-codex/skills/interview-framework-codex - ralph-specum
plugins/ralph-specum-codex/skills/ralph-specum - ralph-specum-cancel
plugins/ralph-specum-codex/skills/ralph-specum-cancel - ralph-specum-design
plugins/ralph-specum-codex/skills/ralph-specum-design - ralph-specum-feedback
plugins/ralph-specum-codex/skills/ralph-specum-feedback - ralph-specum-help
plugins/ralph-specum-codex/skills/ralph-specum-help - ralph-specum-implement
plugins/ralph-specum-codex/skills/ralph-specum-implement - ralph-specum-index
plugins/ralph-specum-codex/skills/ralph-specum-index - ralph-specum-prototype
plugins/ralph-specum-codex/skills/ralph-specum-prototype - ralph-specum-refactor
plugins/ralph-specum-codex/skills/ralph-specum-refactor - ralph-specum-requirements
plugins/ralph-specum-codex/skills/ralph-specum-requirements - ralph-specum-research
plugins/ralph-specum-codex/skills/ralph-specum-research - ralph-specum-start
plugins/ralph-specum-codex/skills/ralph-specum-start - ralph-specum-status
plugins/ralph-specum-codex/skills/ralph-specum-status - ralph-specum-switch
plugins/ralph-specum-codex/skills/ralph-specum-switch - ralph-specum-tasks
plugins/ralph-specum-codex/skills/ralph-specum-tasks - ralph-specum-triage
plugins/ralph-specum-codex/skills/ralph-specum-triage - communication-style
plugins/ralph-specum/skills/communication-style - interview-framework
plugins/ralph-specum/skills/interview-framework - reality-verification
plugins/ralph-specum/skills/reality-verification - smart-ralph
plugins/ralph-specum/skills/smart-ralph - spec-workflow
plugins/ralph-specum/skills/spec-workflow
How it works
communication-style
When your agent uses it
Output rules for all agents - concise, scannable, actionable. Based on Matt Pocock's planning principles.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
692 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Rule
- Why
- Output Rules
- Anti-Patterns
- Examples
- SpecKit-Specific Guidelines
Scripts executed separately
../../hooks/scripts/stop-watcher.sh../../../ralph-specum/hooks/scripts/load-spec-context.sh../../../ralph-specum/hooks/scripts/phase-task-guard.sh../../../ralph-specum/hooks/scripts/quick-mode-guard.sh../../../ralph-specum/hooks/scripts/stop-watcher.sh
Files
../../../../.claude-plugin/marketplace.jsonasset1,210 bytes../../.claude-plugin/plugin.jsonasset378 bytes../../hooks/hooks.jsonasset242 bytes../../hooks/scripts/stop-watcher.shruns7,782 bytesSKILL.mdcore2,808 bytes../../../ralph-specum-codex/hooks/hooks.jsonasset212 bytes../../../ralph-specum-codex/hooks/hooks.jsonasset212 bytes../../../ralph-specum/.claude-plugin/plugin.jsonasset434 bytes../../../ralph-specum/hooks/hooks.jsonasset1,108 bytes../../../ralph-specum/hooks/scripts/load-spec-context.shruns6,279 bytes../../../ralph-specum/hooks/scripts/phase-task-guard.shruns5,154 bytes../../../ralph-specum/hooks/scripts/quick-mode-guard.shruns4,115 bytes../../../ralph-specum/hooks/scripts/stop-watcher.shruns21,993 bytes
Read SKILL.md
# Communication Style
## Core Rule
**Be extremely concise. Sacrifice grammar for concision.**
## Why
- Plans shouldn't be novels
- Terminal reads bottom-up
- Scanning > reading
- Less tokens = faster, cheaper
## Output RulesView the complete source on GitHubdelegation-principle
When your agent uses it
Core principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagents.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
569 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Rule
- Your ONLY Role
- NEVER Do
- ALWAYS Do
- SpecKit Subagent Types
- Why This Matters
- Quick Mode Exception?
- Coordinator Pattern
- Phase Transitions
Files
SKILL.mdcore2,537 bytesSKILL.mdcore2,537 bytes
Read SKILL.md
# Delegation Principle
## Core Rule
**YOU MUST NEVER IMPLEMENT ANYTHING YOURSELF**
The main agent (you) is a **coordinator**, not an implementer.
## Your ONLY Role
1. Parse user input, determine intent
2. Read state files for context
3. **Delegate ALL work to subagents via Task tool**
4. Report results to userView the complete source on GitHubsmart-ralph
When your agent uses it
Core Smart Ralph skill defining common arguments, execution modes, and shared behaviors across all Ralph plugins.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
949 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Common Arguments
- Argument Parsing Rules
- Execution Modes
- State File Structure
- Commit Behavior
- Execution Loop (Self-Contained)
- Task Completion Protocol
- Error Handling
- Branch Management
Files
SKILL.mdcore4,105 bytes
Read SKILL.md
# Smart Ralph
Core skill for all Ralph plugins. Defines common arguments, execution modes, and shared behaviors.
## Common Arguments
All Ralph commands support these standard arguments:
| Argument | Short | Description | Default |
|----------|-------|-------------|---------|
| `--quick` | `-q` | Skip interactive phases, auto-generate artifacts, start execution immediately | false |
| `--commit` | `-c` | Commit and push spec/feature files after generation | true (normal), false (quick) |
| `--no-commit` | | Explicitly disable committing files | - |
| `--max-task-iterations` | `-m` | Max retries per failed task before stopping | 5 |View the complete source on GitHubspeckit-workflow
When your agent uses it
Comprehensive understanding of the spec-kit methodology. Constitution-driven feature development with specify, plan, tasks, and implement phases.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
1,855 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Philosophy
- Directory Structure
- Feature ID System
- Workflow Phases
- State Management
- Quality Assurance
- Command Reference
- Agent Ecosystem
- Constitution Integration
- Best Practices
Files
SKILL.mdcore7,857 bytes
Read SKILL.md
# SpecKit Workflow
The SpecKit methodology is a constitution-driven approach to feature development. It ensures consistency across features by grounding all decisions in project principles.
## Core Philosophy
**Constitution First**: Every feature is designed against the project's constitution - a living document of principles, constraints, and standards.
**Governance Over Convention**: Rather than implicit patterns, SpecKit makes governance explicit through:
- Constitution principles (MUST, SHOULD, MAY)
- Feature specifications tied to principles
- Quality checklists as "unit tests for requirements"
- Consistency analysis across artifacts
View the complete source on GitHubinterview-framework-codex
When your agent uses it
Internal Ralph Specum contract for Codex phase interviews, skill manifests, approval, and delegation gates. Phase coordinators load this skill directly; users do not invoke it as a workflow phase.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
856 tokensWhen the skill is activated
Reference documents
3,811 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Completion criterion
- Hard-transition invariant
- Hard boundaries
- Preload boundary
Files
SKILL.mdcore4,315 bytesagents/openai.yamlasset280 bytesreferences/algorithm.mddoc15,861 bytesreferences/domain-modeling.mddoc2,171 bytes
Read SKILL.md
# Codex interview framework
Run every normal-mode `start`, `triage`, `research`, `requirements`, `design`, and `tasks` phase through `references/algorithm.md` and `references/domain-modeling.md`.
## Completion criterion
Delegate only after all of these conditions hold for one identity tuple:
- `phase`, `interviewId`, `discoveryRevision`, and `contextDigest` match in state and in the delegation packet.
- The selected skill manifest has status `complete` or `partial_warned`.
- The phase interview has status `complete` or `skipped` after explicit final approval.
- `phase_gate.py check-delegation` succeeds.
## Hard-transition invariantView the complete source on GitHubralph-specum
When your agent uses it
Use only when the user explicitly invokes `$ralph-specum`, requests Ralph Specum in Codex, or asks Ralph Specum to handle a named phase or optional prototype.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
2,135 tokensWhen the skill is activated
Reference documents
6,334 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Read These References
- Use These Helpers
- Primary Routing
- Core Rules
- Stop Enforcement
- Response Handoff
- Current Workflow Expectations
- Bootstrap
Files
../../references/prototype-coordinator.mddoc12,392 bytes../../references/workflow.mddoc17,002 bytesSKILL.mdcore9,645 bytesSKILL.mdcore9,645 bytesagents/openai.yamlasset1,009 bytes
Read SKILL.md
# Ralph Specum
Use this as the primary Codex surface for Ralph Specum. It carries the full reusable workflow and can handle the entire command surface directly when helper skills are not installed.
Derive `RALPH_CODEX_PLUGIN_ROOT` from this loaded skill: take the directory containing `SKILL.md`, then its parent `skills` directory, then the next parent. Never derive the plugin root from the project working directory.
## Read These References
- `"$RALPH_CODEX_PLUGIN_ROOT/references/workflow.md"` for the phase flow, branch and worktree behavior, quick mode, and command routing
- `"$RALPH_CODEX_PLUGIN_ROOT/references/state-contract.md"` for `.ralph-state.json`, `.progress.md`, commit rules, and resume semantics
- `"$RALPH_CODEX_PLUGIN_ROOT/references/path-resolution.md"` for `specs_dirs`, `.current-spec`, ambiguity handling, and default directory behavior
- `"$RALPH_CODEX_PLUGIN_ROOT/references/parity-matrix.md"` for Claude-to-Codex feature translation and command mapping
- `"$RALPH_CODEX_PLUGIN_ROOT/references/prototype-coordinator.md"` for direct, suggested, resume, quick, cancel, and prototype handoff behavior
- `"$RALPH_CODEX_PLUGIN_ROOT/skills/interview-framework-codex/SKILL.md"` and its required algorithm and domain-modeling references for every normal-mode phase interviewView the complete source on GitHubralph-specum-cancel
When your agent uses it
This skill should be used only when the user explicitly asks to use `$ralph-specum-cancel`, or explicitly asks Ralph Specum in Codex to stop execution or remove a spec.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
930 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Contract
- Action
Files
SKILL.mdcore4,635 bytesSKILL.mdcore4,635 bytesSKILL.mdcore4,635 bytesagents/openai.yamlasset314 bytes
Read SKILL.md
# Ralph Specum Cancel
Use this to stop execution safely and optionally remove a spec. Safe cancel preserves the spec and every prototype source path.
Derive `RALPH_CODEX_PLUGIN_ROOT` from this loaded skill by resolving two parent directories from the `SKILL.md` directory. Never derive it from the project working directory.
## Contract
- Resolve the target by explicit path, exact name, or `.current-spec`
- Treat a missing `activePrototypes` field as an empty map
- Publish reviewed immutable cancellation evidence before removing active state
- Confirm the exact local target before any deletion
- Never delete a remote branch or perform another remote action
- Do not guess on ambiguous namesView the complete source on GitHubralph-specum-design
When your agent uses it
This skill should be used only when the user explicitly asks to use `$ralph-specum-design`, or explicitly asks Ralph Specum in Codex to run the design phase.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
1,258 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Contract
- Action
- Output Shape
- Response Handoff
Files
SKILL.mdcore5,917 bytesSKILL.mdcore5,917 bytesagents/openai.yamlasset1,012 bytes
Read SKILL.md
# Ralph Specum Design
You are a **coordinator, not an architect** -- delegate ALL work to an `architect-reviewer` sub-agent.
Derive `RALPH_CODEX_PLUGIN_ROOT` from this loaded skill by resolving two parent directories from the `SKILL.md` directory. Never derive it from the project working directory.
## Contract
- Resolve the active spec by explicit path, exact name, or `.current-spec`
- Require `requirements.md`
- Merge state fields only
- Keep the Ralph disk contract unchanged
## ActionView the complete source on GitHubralph-specum-feedback
When your agent uses it
This skill should be used only when the user explicitly asks to use `$ralph-specum-feedback`, or explicitly asks Ralph Specum in Codex to draft or submit feedback.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
204 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Action
- Output
Files
SKILL.mdcore927 bytesagents/openai.yamlasset241 bytes
Read SKILL.md
# Ralph Specum Feedback
Use this to capture product feedback or bug reports for Ralph Specum.
## Action
1. Summarize the issue, request, or missing behavior.
2. Gather the minimum reproducible context, affected files, commands, environment details, and whether the issue is on the Codex package or Claude plugin surface.
3. If `gh` is available and the user wants submission, create a GitHub issue.
4. If `gh` is unavailable or the user only wants a draft, produce a ready-to-paste issue body and the repository issue URL.
## Output
Keep the report concrete. Include expected behavior, actual behavior, reproduction steps, and any relevant state files or logs.View the complete source on GitHubralph-specum-help
When your agent uses it
This skill should be used only when the user explicitly asks to use `$ralph-specum-help`, or explicitly asks Ralph Specum in Codex for help or command guidance.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
767 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Cover
- Optional Prototype Overlay
- Guidance
Files
SKILL.mdcore3,546 bytesSKILL.mdcore3,546 bytesSKILL.mdcore3,546 bytesSKILL.mdcore3,546 bytesSKILL.mdcore3,546 bytesagents/openai.yamlasset268 bytes
Read SKILL.md
# Ralph Specum Help
Use this to explain the Ralph Specum surface in Codex.
## Cover
- Primary skill: `$ralph-specum`
- Helper skills: `$ralph-specum-start`, `$ralph-specum-triage`, `$ralph-specum-research`, `$ralph-specum-requirements`, `$ralph-specum-design`, `$ralph-specum-tasks`, `$ralph-specum-prototype`, `$ralph-specum-implement`, `$ralph-specum-status`, `$ralph-specum-switch`, `$ralph-specum-cancel`, `$ralph-specum-index`, `$ralph-specum-refactor`, `$ralph-specum-feedback`, `$ralph-specum-help`
- Normal flow: start goal grill, approval, research, artifact approval, requirements grill, approval, design grill, approval, tasks grill, approval, implement
- Large effort flow: triage, then start each unblocked spec
- Quick mode: only exact `--quick` bypasses interview questions; exact `--interactive` clears it. Discovery, skill loads, and artifact write gates still run
- Disk contract: `./specs` or configured roots, `.current-spec`, optional `.current-epic`, per-spec markdown files, `.ralph-state.json`
## Optional Prototype OverlayView the complete source on GitHubralph-specum-implement
When your agent uses it
This skill should be used only when the user explicitly asks to use `$ralph-specum-implement`, or explicitly asks Ralph Specum in Codex to run implementation for approved tasks, quick mode, or an explicit continue request.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
1,195 tokensWhen the skill is activated
Reference documents
3,823 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Contract
- Action
- Resume Rules
Files
../../references/workflow.mddoc17,002 bytesSKILL.mdcore5,561 bytesSKILL.mdcore5,561 bytesagents/openai.yamlasset405 bytes
Read SKILL.md
# Ralph Specum Implement
You are a **coordinator, not an executor** -- delegate each task to a `spec-executor` sub-agent.
## Contract
- Resolve the active spec by explicit path, exact name, or `.current-spec`
- Require `tasks.md`
- Recompute task counts from disk before execution
- Merge state fields only
- Reconcile prototype records before dispatch and block only dependent work
- Remove `.ralph-state.json` only when all tasks are complete, verified, and `activePrototypes` is empty
## ActionView the complete source on GitHubralph-specum-index
When your agent uses it
This skill should be used only when the user explicitly asks to use `$ralph-specum-index`, or explicitly asks Ralph Specum in Codex to generate or refresh index artifacts.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
336 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Contract
- Action
- Response Handoff
Files
SKILL.mdcore1,498 bytesagents/openai.yamlasset316 bytes
Read SKILL.md
# Ralph Specum Index
Use this to generate searchable index specs for an existing codebase.
## Contract
- Index output lives under `specs/.index/`
- Use stable Ralph templates for `index.md`, component specs, and external specs
- Keep component and external entries deterministic and easy to diff
## Action
1. Parse the user scope such as path, types, excludes, quick mode, dry run, or force.
2. Scan the requested code areas for controllers, services, models, helpers, migrations, or comparable project structures.View the complete source on GitHubralph-specum-prototype
When your agent uses it
This skill should be used only when the user explicitly invokes `$ralph-specum-prototype`, or explicitly asks Ralph Specum in Codex to run, resume, quick-run, or cancel an optional prototype.
What it loads into context
Frontmatter
64 tokensAlways available to the agent
SKILL.md
538 tokensWhen the skill is activated
Reference documents
2,511 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Load the contract
- Route the request
- Completion gate
Files
../../references/prototype-coordinator.mddoc12,392 bytesSKILL.mdcore2,543 bytesSKILL.mdcore2,543 bytesSKILL.mdcore2,543 bytesSKILL.mdcore2,543 bytesagents/openai.yamlasset297 bytes
Read SKILL.md
# Ralph Specum Prototype
Coordinate one optional prototype overlay. Delegate source work to a child agent and keep the main Ralph phase unchanged until the recorded handoff.
## Load the contract
Derive `RALPH_CODEX_PLUGIN_ROOT` from this loaded skill: take the directory containing `SKILL.md`, then its parent `skills` directory, then the next parent. Never derive the plugin root from the project working directory.
Read `../../references/prototype-coordinator.md` from this skill directory completely before any prototype mutation. Treat it as the source of truth for direct, suggested, resume, quick, cancel, isolation, review, publication, and handoff behavior.
## Route the request
1. Resolve an explicit path, exact spec name, or `.current-spec` with `"$RALPH_CODEX_PLUGIN_ROOT/scripts/resolve_spec_paths.py"`. Use only the returned `basePath`, `specRoot`, settings, and warnings.
2. Parse one mode: direct by default, suggested with a return phase, resume by ID, quick, or cancel by ID.View the complete source on GitHubralph-specum-refactor
When your agent uses it
This skill should be used only when the user explicitly asks to use `$ralph-specum-refactor`, or explicitly asks Ralph Specum in Codex to revise spec artifacts after implementation learnings.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
551 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Contract
- Action
- Response Handoff
Files
SKILL.mdcore2,452 bytesagents/openai.yamlasset413 bytes
Read SKILL.md
# Ralph Specum Refactor
You are a **coordinator, not a refactor specialist** -- delegate spec revision to a `refactor-specialist` sub-agent.
## Contract
- Resolve the active spec by explicit path, exact name, or `.current-spec`
- Review files in order: `requirements.md`, `design.md`, `tasks.md`
- Cascade downstream updates when upstream content changes
- Reconcile `activePrototypes` and preserve unrelated refactor work
## Action
1. Resolve the target spec.View the complete source on GitHubralph-specum-requirements
When your agent uses it
This skill should be used only when the user explicitly asks to use `$ralph-specum-requirements`, or explicitly asks Ralph Specum in Codex to run the requirements phase.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
1,376 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Contract
- Action
- Output Shape
- Response Handoff
Files
SKILL.mdcore6,610 bytesagents/openai.yamlasset1,109 bytes
Read SKILL.md
# Ralph Specum Requirements
You are a **coordinator, not a product manager** -- delegate ALL work to a `product-manager` sub-agent.
Derive `RALPH_CODEX_PLUGIN_ROOT` from this loaded skill by resolving two parent directories from the `SKILL.md` directory. Never derive it from the project working directory.
## Contract
- Resolve the active spec by explicit path, exact name, or `.current-spec`
- Require the spec directory to exist
- Merge state fields only
- Keep the Ralph disk contract unchanged
## ActionView the complete source on GitHubralph-specum-research
When your agent uses it
This skill should be used only when the user explicitly asks to use `$ralph-specum-research`, or explicitly asks Ralph Specum in Codex to run the research phase.
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
1,172 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Contract
- Action
- Output Shape
- Response Handoff
Files
SKILL.mdcore5,464 bytesSKILL.mdcore5,464 bytesagents/openai.yamlasset1,042 bytes
Read SKILL.md
# Ralph Specum Research
You are a **coordinator, not a researcher** -- delegate ALL work to a `research-analyst` sub-agent.
Derive `RALPH_CODEX_PLUGIN_ROOT` from this loaded skill by resolving two parent directories from the `SKILL.md` directory. Never derive it from the project working directory.
## Contract
- Resolve the active spec by explicit path, exact name, or `.current-spec`
- Respect `.claude/ralph-specum.local.md` when present
- Default specs root is `./specs`
- Keep the canonical Ralph file names
- Merge state fields only
View the complete source on GitHubralph-specum-start
When your agent uses it
This skill should be used only when the user explicitly asks to use `$ralph-specum-start`, or explicitly asks Ralph Specum in Codex to start or resume a spec.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
1,905 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Contract
- Action
- Prototype Reconciliation and Resume
- Branch Isolation
- Response Handoff
Files
SKILL.mdcore8,665 bytesSKILL.mdcore8,665 bytesSKILL.mdcore8,665 bytesagents/openai.yamlasset949 bytes
Read SKILL.md
# Ralph Specum Start
Use this for the `start` and `new` entrypoints.
Derive `RALPH_CODEX_PLUGIN_ROOT` from this loaded skill by resolving two parent directories from the `SKILL.md` directory. Never derive it from the project working directory.
## Contract
- Read `.claude/ralph-specum.local.md` when present
- Default specs root is `./specs`
- Keep `.current-spec` in the default specs root
- Keep the standard Ralph files stable
- Merge `.ralph-state.json`. Do not replace the full object
View the complete source on GitHubralph-specum-status
When your agent uses it
This skill should be used only when the user explicitly asks to use `$ralph-specum-status`, or explicitly asks Ralph Specum in Codex for status or active spec progress.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
656 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Contract
- Action
- Output
Files
SKILL.mdcore2,891 bytesSKILL.mdcore2,891 bytesagents/openai.yamlasset290 bytes
Read SKILL.md
# Ralph Specum Status
Use this to report Ralph state across configured spec roots.
Derive `RALPH_CODEX_PLUGIN_ROOT` from this loaded skill by resolving two parent directories from the `SKILL.md` directory. Never derive it from the project working directory.
## Contract
- Read `.claude/ralph-specum.local.md` when present
- Default specs root is `./specs`
- `.current-spec` lives in the default specs root
- Hidden directories do not count as specs
## ActionView the complete source on GitHubralph-specum-switch
When your agent uses it
This skill should be used only when the user explicitly asks to use `$ralph-specum-switch`, or explicitly asks Ralph Specum in Codex to switch the active spec.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
446 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Contract
- Action
Files
SKILL.mdcore1,918 bytesagents/openai.yamlasset285 bytes
Read SKILL.md
# Ralph Specum Switch
Use this to switch the active spec.
Derive `RALPH_CODEX_PLUGIN_ROOT` from this loaded skill by resolving two parent directories from the `SKILL.md` directory. Never derive it from the project working directory.
## Contract
- Read `.claude/ralph-specum.local.md` when present
- Parse `specs_dirs` from frontmatter to discover all spec roots
- Treat the first `specs_dirs` entry as the default root
- Default specs root is `./specs`
- `.current-spec` lives in the default specs root
- Do not guess on ambiguous namesView the complete source on GitHubralph-specum-tasks
When your agent uses it
This skill should be used only when the user explicitly asks to use `$ralph-specum-tasks`, or explicitly asks Ralph Specum in Codex to run the tasks phase.
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
1,388 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Contract
- Action
- Output Shape
- Response Handoff
Files
SKILL.mdcore6,407 bytesSKILL.mdcore6,407 bytesagents/openai.yamlasset1,107 bytes
Read SKILL.md
# Ralph Specum Tasks
You are a **coordinator, not a task planner** -- delegate ALL work to a `task-planner` sub-agent.
Derive `RALPH_CODEX_PLUGIN_ROOT` from this loaded skill by resolving two parent directories from the `SKILL.md` directory. Never derive it from the project working directory.
## Contract
- Resolve the active spec by explicit path, exact name, or `.current-spec`
- Require `requirements.md` and `design.md`
- Merge state fields only
- Keep the Ralph disk contract unchanged
## ActionView the complete source on GitHubralph-specum-triage
When your agent uses it
This skill should be used only when the user explicitly asks to use `$ralph-specum-triage`, or explicitly asks Ralph Specum in Codex to triage a large effort into multiple specs.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
1,454 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Contract
- Action
- Output Shape
- Stop Behavior
- Response Handoff
Files
SKILL.mdcore6,624 bytesagents/openai.yamlasset972 bytes
Read SKILL.md
# Ralph Specum Triage
You are a **coordinator, not a triage analyst** -- delegate decomposition work to a `triage-analyst` sub-agent.
## Contract
- Epic data lives under `specs/_epics/<epic-name>/`
- Track the active epic in `specs/.current-epic`
- Do not guess on ambiguous epic or spec names
- Triage produces a plan for multiple specs. It does not implement them
## Action
1. Parse exact `--quick` and exact `--interactive` tokens before routing. Reject both together, `-q`, variants, and natural-language substitutes.View the complete source on GitHubcommunication-style
When your agent uses it
This skill should be used when generating spec artifacts (research.md, requirements.md, design.md, tasks.md), formatting agent output, structuring phase results, or when any Ralph agent needs guidance on concise, scannable output formatting. Applies to all Ralph spec phase agents.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
521 tokensWhen the skill is activated
Reference documents
458 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Rationale
- Output Rules
- Anti-Patterns
- References
Files
SKILL.mdcore2,202 bytesreferences/examples.mddoc1,978 bytes
Read SKILL.md
# Communication Style
Be extremely concise. Sacrifice grammar for concision.
## Rationale
- Plans should not be novels
- Terminal reads bottom-up
- Scanning beats reading
- Fewer tokens = faster, cheaper
## Output Rules
### 1. Brevity FirstView the complete source on GitHubinterview-framework
When your agent uses it
This skill should be used when a Ralph phase must identify critical user decisions, run a layered grill, persist partial answers, obtain explicit approval, or resume an interrupted phase interview before delegating artifact work.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
1,749 tokensWhen the skill is activated
Reference documents
5,231 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Entry Contract
- Critical Decision Test
- Build the Design Tree and Traverse the Layered Frontier
- Domain Language
- Reply Semantics
- Final Approval
- Artifact Approval
- Persistence
- References
Files
../../references/normal-mode-gates.mddoc13,071 bytesSKILL.mdcore8,888 bytesSKILL.mdcore8,888 bytesSKILL.mdcore8,888 bytesSKILL.mdcore8,888 bytesSKILL.mdcore8,888 bytesreferences/algorithm.mddoc6,252 bytesreferences/domain-modeling.mddoc2,171 bytesreferences/examples.mddoc2,818 bytes
Read SKILL.md
# Interview Framework
Treat every normal-mode interview governed by this framework as a grill. Run the approval-gated interview for `start`, `triage`, `research`, `requirements`, `design`, and `tasks`. Treat this skill and its references as the single source of truth for interview behavior. Phase commands supply exploration territory and artifact context; they do not redefine the algorithm.
Quick mode bypasses interview questions only. It still requires current discovery, contract loading, bypass receipts, delegation checks, and artifact-agent load parity.
## Entry Contract
Before each new or resumed interview:
1. Complete the applicable skill discovery pass from `${CLAUDE_PLUGIN_ROOT}/references/normal-mode-gates.md`.
2. Reload this entire `SKILL.md`, `references/algorithm.md`, `references/domain-modeling.md`, every selected skill body, and every selected skill resource required for the current work. Load `references/examples.md` only when an example is needed.
3. Record the load manifest with `phase_gate.py record-skill-load`.
4. Begin or resume the interview with the matching phase, interview ID, discovery revision, and context digest.View the complete source on GitHubreality-verification
When your agent uses it
This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only tests", or needs guidance on verifying fixes by reproducing failures before and after implementation, or detecting mock-heavy test anti-patterns.
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
872 tokensWhen the skill is activated
Reference documents
1,504 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Goal Detection
- Command Mapping
- BEFORE/AFTER Documentation
- VF Task Format
- Test Quality Checks
- Why This Matters
Files
SKILL.mdcore3,507 bytesreferences/goal-detection-patterns.mddoc2,330 bytesreferences/mock-quality-checks.mddoc3,437 bytes
Read SKILL.md
# Reality Verification
For fix goals: reproduce the failure BEFORE work, verify resolution AFTER.
## Goal Detection
Classify user goals to determine if diagnosis is needed. See `references/goal-detection-patterns.md` for detailed patterns.
**Quick reference:**
- Fix indicators: fix, repair, resolve, debug, patch, broken, failing, error, bug
- Add indicators: add, create, build, implement, new
- Conflict resolution: If both present, treat as Fix
## Command MappingView the complete source on GitHubsmart-ralph
When your agent uses it
This skill should be used when the user asks about "ralph arguments", "quick mode", "commit spec", "max iterations", "ralph state file", "prototype overlay", "execution modes", "ralph loop", "coordinator behavior", "delegate to subagent", or needs guidance on Ralph plugin arguments, state management, delegation patterns, or execution loop behavior. Core behavioral skill for all Ralph Specum operations.
What it loads into context
Frontmatter
110 tokensAlways available to the agent
SKILL.md
1,623 tokensWhen the skill is activated
Reference documents
1,206 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Common Arguments
- Execution Modes
- State File
- Commit Behavior
- Prototype Overlay
- Task Execution Loop
- Error Handling
- Branch Management
- Coordinator Behavior
Files
SKILL.mdcore7,820 bytesSKILL.mdcore7,820 bytesSKILL.mdcore7,820 bytesSKILL.mdcore7,820 bytesSKILL.mdcore7,820 bytesSKILL.mdcore7,820 bytesreferences/state-file-schema.mddoc5,419 bytes
Read SKILL.md
# Smart Ralph
Core skill for all Ralph plugins. Defines common arguments, execution modes, shared behaviors, and coordinator delegation rules.
## Common Arguments
All Ralph commands support these standard arguments:
| Argument | Short | Description | Default |
|----------|-------|-------------|---------|
| `--quick` | | Exact token that enables persistent non-interactive generation | false |
| `--interactive` | | Exact token that clears persistent quick mode | - |
| `--commit` | `-c` | Commit spec/feature files locally after generation | true (normal), false (quick) |
| `--no-commit` | | Explicitly disable committing files | - |View the complete source on GitHubspec-workflow
When your agent uses it
This skill should be used when the user asks to "build a feature", "create a spec", "start spec-driven development", "run research phase", "generate requirements", "create design", "plan tasks", "implement spec", "check spec status", "triage a feature", "create an epic", "decompose a large feature", or needs guidance on spec-driven development workflow, phase ordering, or epic orchestration.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
1,062 tokensWhen the skill is activated
Reference documents
1,464 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Decision Tree: Where to Start
- Single Spec Flow
- Epic Flow (Multi-Spec)
- Management Commands
- Common Workflows
- References
Files
SKILL.mdcore4,579 bytesSKILL.mdcore4,579 bytesSKILL.mdcore4,579 bytesSKILL.mdcore4,579 bytesreferences/phase-transitions.mddoc6,898 bytes
Read SKILL.md
# Spec Workflow
Spec-driven development transforms feature requests into structured specs through sequential phases, then executes them task-by-task.
## Decision Tree: Where to Start
| Situation | Command |
|-----------|---------|
| New feature, want guidance | `/ralph-specum:start <name> <goal>` |
| New feature, skip interviews | `/ralph-specum:start <name> <goal> --quick` |
| Large feature needing decomposition | `/ralph-specum:triage <goal>` |
| Resume existing spec | `/ralph-specum:start` (auto-detects) |
| Jump to specific phase | `/ralph-specum:<phase>` |
View the complete source on GitHubSkills included
- communication-style
- delegation-principle
- smart-ralph
- speckit-workflow
- interview-framework-codex
- ralph-specum
- ralph-specum-cancel
- ralph-specum-design
- ralph-specum-feedback
- ralph-specum-help
- ralph-specum-implement
- ralph-specum-index
- ralph-specum-prototype
- ralph-specum-refactor
- ralph-specum-requirements
- ralph-specum-research
- ralph-specum-start
- ralph-specum-status
- ralph-specum-switch
- ralph-specum-tasks
- ralph-specum-triage
- communication-style
- interview-framework
- reality-verification
- smart-ralph
- spec-workflow
Repository facts
- License
- MIT
- Created
- Jan 11, 2026
- Last pushed
- Oct 28, 2026
- Forks
- 49
- Open issues
- 8
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 42 notes
plugins/ralph-specum-codex/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/ralph-speckit/skills/delegation-principle/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/ralph-specum-codex/hooks/hooks.json:1Plugin-wide analysis incomplete; see repository notesplugins/ralph-specum-codex/hooks/hooks.json:1Plugin-wide analysis incomplete; see repository notesplugins/ralph-specum-codex/hooks/hooks.json:1Plugin-wide analysis incomplete; see repository notesplugins/ralph-specum-codex/skills/ralph-specum/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/ralph-specum-codex/skills/ralph-specum-cancel/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/ralph-specum-codex/skills/ralph-specum-cancel/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/ralph-specum-codex/skills/ralph-specum-design/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/ralph-specum-codex/hooks/hooks.json:1Plugin-wide analysis incomplete; see repository notesplugins/ralph-specum-codex/skills/ralph-specum-help/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/ralph-specum-codex/skills/ralph-specum-help/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/ralph-specum-codex/skills/ralph-specum-help/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/ralph-specum-codex/skills/ralph-specum-help/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/ralph-specum-codex/skills/ralph-specum-implement/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/ralph-specum-codex/hooks/hooks.json:1Plugin-wide analysis incomplete; see repository notesplugins/ralph-specum-codex/skills/ralph-specum-prototype/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/ralph-specum-codex/skills/ralph-specum-prototype/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/ralph-specum-codex/skills/ralph-specum-prototype/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/ralph-specum-codex/hooks/hooks.json:1Plugin-wide analysis incomplete; see repository notes
- No broad tool permissions
- 4 dangerous shell commandsin 2 files: plugins/ralph-specum/hooks/scripts/stop-watcher.sh:204 plugins/ralph-speckit/hooks/scripts/stop-watcher.sh:187
- No network access
- No hidden or obfuscated text
- No instruction overrides
- 5 executable scriptsin 5 files: plugins/ralph-speckit/hooks/scripts/stop-watcher.sh:1 plugins/ralph-specum/hooks/scripts/load-spec-context.sh:1 plugins/ralph-specum/hooks/scripts/phase-task-guard.sh:1 and 2 more
- No access to secrets
- No requests to vote in Hot
Show all 9 signals by file
plugins/ralph-speckit/hooks/scripts/stop-watcher.sh
plugins/ralph-specum/hooks/scripts/load-spec-context.sh
- Executable scriptline 1
#!/bin/bash
plugins/ralph-specum/hooks/scripts/phase-task-guard.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/ralph-specum/hooks/scripts/quick-mode-guard.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/ralph-specum/hooks/scripts/stop-watcher.sh
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: 9 facts
- Executable script in code of a file that runsplugins/ralph-speckit/hooks/scripts/stop-watcher.sh:1High confidence
- Dangerous shell operation in code of a file that runsplugins/ralph-speckit/hooks/scripts/stop-watcher.sh:187High confidence
- Executable script in code of a file that runsplugins/ralph-specum/hooks/scripts/load-spec-context.sh:1High confidence
- Executable script in code of a file that runsplugins/ralph-specum/hooks/scripts/phase-task-guard.sh:1High confidence
- Executable script in code of a file that runsplugins/ralph-specum/hooks/scripts/quick-mode-guard.sh:1High confidence
- Executable script in code of a file that runsplugins/ralph-specum/hooks/scripts/stop-watcher.sh:1High confidence
- Dangerous shell operation in code of a file that runsplugins/ralph-specum/hooks/scripts/stop-watcher.sh:204High confidence
- Dangerous shell operation in code of a file that runsplugins/ralph-specum/hooks/scripts/stop-watcher.sh:232High confidence
- Dangerous shell operation in code of a file that runsplugins/ralph-specum/hooks/scripts/stop-watcher.sh:456High confidence
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 | Native | Path .cursor/skills/Command Development | .cursor/skills/<skill-name>/ |
| Gemini CLI | Native | Path .gemini/skills/Command Development | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Native | Path .github/skills/Command Development | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md plugins/ralph-speckit/skills/communication-style/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.