Not in the top 1,000 by GitHub stars
try-works/recursive-mode
Recursive workflow for agentic engineering. Like Factory Missions but properly recursive, free and open source.
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
skills/recursive-debugging/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ff75bc761d61
No earlier version was observed for comparison.
skills/recursive-mode/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → ff75bc761d61
No earlier version was observed for comparison.
skills/recursive-review-bundle/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ff75bc761d61
No earlier version was observed for comparison.
skills/recursive-router/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ff75bc761d61
No earlier version was observed for comparison.
skills/recursive-spec/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ff75bc761d61
No earlier version was observed for comparison.
skills/recursive-subagent/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ff75bc761d61
No earlier version was observed for comparison.
skills/recursive-tdd/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ff75bc761d61
No earlier version was observed for comparison.
skills/recursive-training/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ff75bc761d61
No earlier version was observed for comparison.
skills/recursive-worktree/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ff75bc761d61
No earlier version was observed for comparison.
Verified commit ff75bc761d614eec978c693b7bf24128ee80ec61
git clone --filter=blob:none --no-checkout https://github.com/try-works/recursive-mode.git .hotskills/try-works-recursive-mode && git -C .hotskills/try-works-recursive-mode checkout --detach ff75bc761d614eec978c693b7bf24128ee80ec61
# Copy each selected skill directory from .hotskills/try-works-recursive-mode into .agents/skills/<skill-name>/Heat
0.4- 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
- recursive-debugging
skills/recursive-debugging - recursive-mode
skills/recursive-mode - recursive-review-bundle
skills/recursive-review-bundle - recursive-router
skills/recursive-router - recursive-spec
skills/recursive-spec - recursive-subagent
skills/recursive-subagent - recursive-tdd
skills/recursive-tdd - recursive-training
skills/recursive-training - recursive-worktree
skills/recursive-worktree
How it works
recursive-debugging
When your agent uses it
Use when a recursive-mode requirement involves debugging a bug, test failure, or unexpected behavior. Insert Phase 1.5 between Phase 1 and Phase 2 to perform systematic root cause analysis before attempting any fixes. Trigger phrases: "debug", "investigate", "failing tests", "crash", "root cause".
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
3,461 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
- Overview
- Trigger examples
- When to Use
- Phase 1.5 Insertion
- The Four Phases of Systematic Debugging
- Routing Awareness
- Red Flags - STOP and Follow Process
- Common Process Shortcuts (STOP)
- If 3+ Fix Attempts Failed
- Phase 1.5 Artifact Template
- Integration with recursive-mode
- References
Files
SKILL.mdcore13,666 bytesSKILL.mdcore13,666 bytesagents/openai.yamlasset229 bytes
Read SKILL.md
# recursive-debugging (Phase 1.5)
## Overview
When a requirement involves fixing a bug or investigating unexpected behavior, ad-hoc fixes waste time and create new bugs. Systematic debugging finds the root cause before any fix is attempted.
**Core Principle:** ALWAYS find root cause before attempting fixes. Symptom fixes are failure.
**The Iron Law for recursive-mode debugging:**
```
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
```
## Trigger examplesView the complete source on GitHubrecursive-mode
When your agent uses it
Repository workflow orchestration skill for staged implementation, locked artifacts, late-phase receipts, and durable memory maintenance. Use when executing recursive-mode runs, resuming a run, locking a phase, or verifying locks.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
3,029 tokensWhen the skill is activated
Reference documents
63,345 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Bootstrap
- Read Order
- Operational Surface
- Trigger Examples
- Utility Scripts
- Subskills
- Router-aware delegated execution
- Optional add-on
Scripts executed separately
scripts/check-reusable-repo-hygiene.ps1scripts/check-reusable-repo-hygiene.pyscripts/install-recursive-mode.ps1scripts/install-recursive-mode.pyscripts/install-recursive-mode.shscripts/lint-recursive-run.ps1scripts/lint-recursive-run.pyscripts/recursive-closeout.ps1scripts/recursive-closeout.pyscripts/recursive-init.ps1scripts/recursive-init.pyscripts/recursive-lock.ps1scripts/recursive-lock.pyscripts/recursive-review-bundle.ps1scripts/recursive-review-bundle.pyscripts/recursive-router-cli-configure.ps1scripts/recursive-router-cli-configure.pyscripts/recursive-router-cli-init.ps1scripts/recursive-router-cli-init.pyscripts/recursive-router-cli-invoke.ps1scripts/recursive-router-cli-invoke.pyscripts/recursive-router-cli-probe.ps1scripts/recursive-router-cli-probe.pyscripts/recursive-router-cli-resolve.ps1scripts/recursive-router-cli-resolve.pyscripts/recursive-router-cli-validate.ps1scripts/recursive-router-cli-validate.pyscripts/recursive-router-configure.ps1scripts/recursive-router-configure.pyscripts/recursive-router-init.ps1scripts/recursive-router-init.pyscripts/recursive-router-invoke.ps1scripts/recursive-router-invoke.pyscripts/recursive-router-probe.ps1scripts/recursive-router-probe.pyscripts/recursive-router-resolve.ps1scripts/recursive-router-resolve.pyscripts/recursive-router-validate.ps1scripts/recursive-router-validate.pyscripts/recursive-status.ps1scripts/recursive-status.pyscripts/recursive-subagent-action.ps1scripts/recursive-subagent-action.pyscripts/recursive-training-extract.ps1scripts/recursive-training-extract.pyscripts/recursive-training-grpo.ps1scripts/recursive-training-grpo.pyscripts/recursive-training-loader.ps1scripts/recursive-training-loader.pyscripts/recursive-training-mcp.ps1scripts/recursive-training-mcp.pyscripts/recursive-training-phase8-trigger.ps1scripts/recursive-training-phase8-trigger.pyscripts/recursive-training-sync.ps1scripts/recursive-training-sync.pyscripts/recursive_phase_rules.pyscripts/recursive_router_cli_lib.pyscripts/recursive_router_lib.pyscripts/verify-locks.ps1scripts/verify-locks.py
Files
../recursive-debugging/SKILL.mddoc13,666 bytesSKILL.mdcore13,526 bytesSKILL.mdcore13,526 bytesSKILL.mdcore13,526 bytesSKILL.mdcore13,526 bytesSKILL.mdcore13,526 bytesSKILL.mdcore13,526 bytesSKILL.mdcore13,526 bytesagents/openai.yamlasset202 bytesreferences/agents-block.mddoc7,578 bytesreferences/artifact-template.mddoc72,510 bytesreferences/bootstrap/RECURSIVE.mddoc110,449 bytesreferences/local-first-web-app-checklist.mddoc1,653 bytesscripts/check-reusable-repo-hygiene.ps1runs625 bytesscripts/check-reusable-repo-hygiene.pyruns9,199 bytesscripts/install-recursive-mode.ps1runs36,838 bytesscripts/install-recursive-mode.pyruns32,476 bytesscripts/install-recursive-mode.shruns1,683 bytesscripts/lint-recursive-run.ps1runs739 bytesscripts/lint-recursive-run.pyruns130,503 bytesscripts/recursive-closeout.ps1runs1,015 bytesscripts/recursive-closeout.pyruns24,808 bytesscripts/recursive-init.ps1runs19,138 bytesscripts/recursive-init.pyruns12,874 bytesscripts/recursive-lock.ps1runs677 bytesscripts/recursive-lock.pyruns12,852 bytesscripts/recursive-review-bundle.ps1runs2,995 bytesscripts/recursive-review-bundle.pyruns22,655 bytesscripts/recursive-router-cli-configure.ps1runs86 bytesscripts/recursive-router-cli-configure.pyruns230 bytesscripts/recursive-router-cli-init.ps1runs81 bytesscripts/recursive-router-cli-init.pyruns225 bytesscripts/recursive-router-cli-invoke.ps1runs83 bytesscripts/recursive-router-cli-invoke.pyruns227 bytesscripts/recursive-router-cli-probe.ps1runs82 bytesscripts/recursive-router-cli-probe.pyruns226 bytesscripts/recursive-router-cli-resolve.ps1runs84 bytesscripts/recursive-router-cli-resolve.pyruns228 bytesscripts/recursive-router-cli-validate.ps1runs85 bytesscripts/recursive-router-cli-validate.pyruns229 bytesscripts/recursive-router-configure.ps1runs798 bytesscripts/recursive-router-configure.pyruns2,880 bytesscripts/recursive-router-init.ps1runs490 bytesscripts/recursive-router-init.pyruns925 bytesscripts/recursive-router-invoke.ps1runs1,553 bytesscripts/recursive-router-invoke.pyruns4,544 bytesscripts/recursive-router-probe.ps1runs735 bytesscripts/recursive-router-probe.pyruns1,684 bytesscripts/recursive-router-resolve.ps1runs803 bytesscripts/recursive-router-resolve.pyruns1,650 bytesscripts/recursive-router-validate.ps1runs494 bytesscripts/recursive-router-validate.pyruns804 bytesscripts/recursive-status.ps1runs674 bytesscripts/recursive-status.pyruns100,014 bytesscripts/recursive-subagent-action.ps1runs5,914 bytesscripts/recursive-subagent-action.pyruns12,707 bytesscripts/recursive-training-extract.ps1runs735 bytesscripts/recursive-training-extract.pyruns3,598 bytesscripts/recursive-training-grpo.ps1runs1,305 bytesscripts/recursive-training-grpo.pyruns58,438 bytesscripts/recursive-training-loader.ps1runs2,308 bytesscripts/recursive-training-loader.pyruns21,002 bytesscripts/recursive-training-mcp.ps1runs721 bytesscripts/recursive-training-mcp.pyruns10,334 bytesscripts/recursive-training-phase8-trigger.ps1runs1,402 bytesscripts/recursive-training-phase8-trigger.pyruns4,964 bytesscripts/recursive-training-sync.ps1runs735 bytesscripts/recursive-training-sync.pyruns7,116 bytesscripts/recursive_phase_rules.pyruns13,013 bytesscripts/recursive_router_cli_lib.pyruns77 bytesscripts/recursive_router_lib.pyruns86,576 bytesscripts/verify-locks.ps1runs733 bytesscripts/verify-locks.pyruns14,145 bytes../recursive-review-bundle/SKILL.mddoc3,489 bytes../recursive-router/SKILL.mddoc21,404 bytes../recursive-spec/SKILL.mddoc5,686 bytes../recursive-subagent/SKILL.mddoc12,090 bytes../recursive-tdd/SKILL.mddoc11,005 bytes../recursive-training/SKILL.mddoc7,418 bytes../recursive-worktree/SKILL.mddoc4,734 bytes
Read SKILL.md
# recursive-mode
## Purpose
Use this skill to run the repository workflow defined in `/.recursive/RECURSIVE.md`.
This file is the installable entrypoint for the skill. It is not the canonical workflow spec.
For phase order, audit-loop rules, lock rules, addenda, late-phase receipts, state/decisions updates, and memory maintenance, follow `/.recursive/RECURSIVE.md`.
## Bootstrap
Before doing recursive-mode work, ensure the repo scaffold exists:
- `/.recursive/RECURSIVE.md`View the complete source on GitHubrecursive-review-bundle
When your agent uses it
Use when recursive-mode work needs a canonical delegated-review or audit handoff. Generates reproducible review bundles for Phase 3.5 code review, test review, or other delegated checks using the repo review-bundle scripts.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
827 tokensWhen the skill is activated
Reference documents
2,489 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Canonical Scripts
- Minimum Inputs
- Typical Commands
- Acceptance Rules
- Routing Awareness
- References
Files
SKILL.mdcore3,489 bytesSKILL.mdcore3,489 bytesSKILL.mdcore3,489 bytesagents/openai.yamlasset242 bytes../recursive-subagent/SKILL.mddoc12,090 bytes
Read SKILL.md
# recursive-review-bundle
Use this skill to prepare a canonical review bundle before delegating an audit or review in `recursive-mode`.
This skill does not replace `/.recursive/RECURSIVE.md`. It packages the context bundle that delegated reviewers need so the review is durable, reproducible, and acceptable to the workflow.
## Canonical Scripts
Use the repo scripts:
- `./.recursive/scripts/recursive-review-bundle.py`
- `./.recursive/scripts/recursive-review-bundle.ps1`
Prefer the Python script when both toolchains are available. Use the PowerShell wrapper when the delegated path is already PowerShell-oriented.View the complete source on GitHubrecursive-router
When your agent uses it
Use when recursive-mode needs to route delegated audit, review, or bounded implementation work through external transports, CLIs, and models while preserving controller verification and fallback behavior.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
4,543 tokensWhen the skill is activated
Reference documents
2,489 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Controller Boundary
- Invocation Boundary
- Purpose
- Trigger Examples
- Canonical Paths
- Canonical Roles
- Read Order
- Required Behavior
- Discovery
- Recommended Routing Workflow
- Delegation Payload Shape
- User Prompting
- Fallback Behavior
- Auditability
- Warnings
Files
SKILL.mdcore21,404 bytesSKILL.mdcore21,404 bytesSKILL.mdcore21,404 bytesSKILL.mdcore21,404 bytesSKILL.mdcore21,404 bytesSKILL.mdcore21,404 bytesSKILL.mdcore21,404 bytesagents/openai.yamlasset264 bytes../recursive-subagent/SKILL.mddoc12,090 bytes
Read SKILL.md
# recursive-router
Use this skill when `recursive-mode` and `recursive-subagent` have already established a delegated role and you want the route to be driven by a user-editable CLI/model policy instead of ad hoc controller choice.
This skill does **not** relax recursive-mode. Routed external output is still untrusted until the main agent verifies it against actual files, actual diffs, and actual recursive artifacts.
## Controller Boundary
The main orchestrator remains the model the user is currently interacting with in their CLI, IDE, or agent session.
`recursive-router` does **not** become a second orchestrator or a second workflow spec. It only helps the current controller choose and invoke an external CLI/model for a bounded delegated role.
The current controller remains responsible for:
View the complete source on GitHubrecursive-spec
When your agent uses it
Approval-gated, repo-aware requirements/spec authoring for new recursive-mode runs. Use when the user wants help creating a plan, spec, scope, or requirements for work that does not yet have a run, especially prompts like "create a plan", "help me plan", "create a spec", "write requirements", or similar derivatives.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
1,234 tokensWhen the skill is activated
Reference documents
19,183 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Primary Use Case
- Conversation Contract
- Draft Handling Before Approval
- Required Read Behavior
- Authoring Flow
- Quality Rules
- Output Contract
- Run Creation Rule
- Routing Awareness
- Boundaries
- References
Files
../recursive-mode/references/artifact-template.mddoc72,510 bytesSKILL.mdcore5,686 bytesagents/openai.yamlasset229 bytesreferences/patterns.mddoc3,913 bytes
Read SKILL.md
# recursive-spec
Use this skill to co-author a repo-aware `00-requirements.md` for a new recursive-mode run.
This skill is for **requirements/spec authoring before implementation starts**. It does not replace `/.recursive/RECURSIVE.md`, and it should not skip ahead to Phase 2 planning or Phase 3 implementation.
## Primary Use Case
Use `recursive-spec` when the user wants help shaping work before a run exists, especially with prompts like:
- `create a plan`
- `help me plan`
- `create a spec`
- `write requirements`View the complete source on GitHubrecursive-subagent
When your agent uses it
Use when recursive-mode work may benefit from delegated audit, review, or bounded implementation support. This skill prioritizes analyst, planner, code-reviewer, memory-auditor, tester, and implementer roles, with mandatory self-audit fallback when subagents are unavailable.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
2,489 tokensWhen the skill is activated
Reference documents
25,766 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Priority Of Use
- Capability Detection Is A Hard Control Point
- Canonical Constraints
- Delegated Audit Contract
- Controller Checklist
- Recommended Roles
- Handoff Template
- Self-Audit Fallback Pattern
- Output Rejection Rules
- References
Files
../recursive-mode/references/artifact-template.mddoc72,510 bytes../recursive-router/SKILL.mddoc21,404 bytesSKILL.mdcore12,090 bytesagents/code-reviewer.mddoc6,210 bytesagents/implementer.mddoc6,450 bytesagents/openai.yamlasset255 bytes
Read SKILL.md
# recursive-subagent
Use this skill to decide whether subagents help a recursive-mode phase and to enforce the handoff contract when they do.
This skill does not relax the canonical workflow. The main agent remains responsible for:
- one active recursive phase at a time
- serving as the single orchestrator the user is currently interacting with
- full audit rigor before lock
- rejecting incomplete or context-free subagent output
- falling back to `self-audit` when subagents are unavailable
If `recursive-router` is installed, consult it when the user has explicitly asked to use routing or when an active configured external route exists for the selected delegated role. Because router discovery and configuration may inspect local CLI and provider configuration on the device, ask the user first before new setup or policy changes. Do not ask again merely to honor an already configured external route for a role that must now be dispatched.
View the complete source on GitHubrecursive-tdd
When your agent uses it
Use when implementing any code in recursive-mode Phase 3. Enforces strict RED-GREEN-REFACTOR discipline with The Iron Law - no production code without a failing test first. Trigger phrases: "implement this", "add feature", "fix bug", "write a failing test", "TDD".
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
2,801 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
- Overview
- Trigger examples
- When to Use
- RED-GREEN-REFACTOR Cycle
- Common Process Shortcuts (STOP)
- Red Flags - STOP and Start Over
- Integration with recursive-mode Phase 3
- Routing Awareness
- Bug Fix TDD Procedure
- Example: Complete Phase 3 TDD Section
- Verification
Files
SKILL.mdcore11,005 bytesSKILL.mdcore11,005 bytesSKILL.mdcore11,005 bytesSKILL.mdcore11,005 bytesagents/openai.yamlasset230 bytes
Read SKILL.md
# recursive-tdd
## Overview
Test-Driven Development is mandatory for all recursive-mode implementation work. This skill ensures test-first discipline is followed rigorously and recorded in a way recursive-mode tooling can verify.
**Core Principle:** If you didn't watch the test fail, you don't know if it tests the right thing.
**The Iron Law for recursive-mode:**
```
NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST
```
## Trigger examplesView the complete source on GitHubrecursive-training
When your agent uses it
Use after completed recursive-mode runs accumulate to extract durable experiential memory into `/.recursive/memory/`, then load it for later runs through the canonical loader.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
1,636 tokensWhen the skill is activated
Reference documents
1,929 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to use it
- Hard rules
- Training model
- Phase 8 and loading boundary
- Commands
- Trigger patterns
- Operator checklist
- Script surface
- Detailed references
- Coverage Gate
- Approval Gate
Files
SKILL.mdcore7,418 bytesSKILL.mdcore7,418 bytesSKILL.mdcore7,418 bytesSKILL.mdcore7,418 bytesSKILL.mdcore7,418 bytesSKILL.mdcore7,418 bytesSKILL.mdcore7,418 bytesSKILL.mdcore7,418 bytesagents/openai.yamlasset270 bytesreferences/memory-architecture.mddoc4,553 bytesreferences/phase8-and-loading.mddoc4,351 bytes
Read SKILL.md
# recursive-training
## Purpose
Use this skill after a repository has accumulated completed recursive-mode runs and you want to turn repeated successes or failures into durable, repo-local guidance.
The canonical workflow still lives in `/.recursive/RECURSIVE.md`. This skill owns only the training, loading, and memory-discipline layer that sits around completed runs.
## When to use it
Use `recursive-training` to:
- extract cross-run learnings from completed recursive-mode runs
- keep those learnings in `/.recursive/memory/` instead of ad hoc mirrorsView the complete source on GitHubrecursive-worktree
When your agent uses it
Use when starting any recursive-mode requirement to set up an isolated git worktree. Required before implementation phases: create an isolated workspace, verify a clean baseline, and keep main/master clean.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
1,048 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
- Purpose
- Hard Rule
- Default Location Order
- Main Branch Protection
- Minimum Phase 0 Checklist
- Suggested Commands
- Setup Guidance
- Router State In Worktrees
- Output Contract
- Routing Awareness
- Integration
Files
SKILL.mdcore4,734 bytesSKILL.mdcore4,734 bytesSKILL.mdcore4,734 bytesSKILL.mdcore4,734 bytesSKILL.mdcore4,734 bytesSKILL.mdcore4,734 bytesSKILL.mdcore4,734 bytesSKILL.mdcore4,734 bytesSKILL.mdcore4,734 bytesSKILL.mdcore4,734 bytesagents/openai.yamlasset233 bytes
Read SKILL.md
# recursive-worktree
## Purpose
Use this skill at the start of a recursive-mode run to set up an isolated worktree before Phase 1+ work begins.
The canonical overall workflow still lives in `/.recursive/RECURSIVE.md`. This skill covers only the worktree-isolation discipline for `00-worktree.md`.
## Hard Rule
Do not proceed with recursive-mode phase work until:
1. A feature-branch worktree exists.
2. The worktree directory is git-ignored if it lives inside the repo.View the complete source on GitHubSkills included
- recursive-debugging
- recursive-mode
- recursive-review-bundle
- recursive-router
- recursive-spec
- recursive-subagent
- recursive-tdd
- recursive-training
- recursive-worktree
Repository facts
- License
- Apache-2.0
- Created
- Apr 6, 2026
- Last pushed
- Jul 24, 2026
- Forks
- 12
- Open issues
- 0
- Project activity
- Slowing
Before you install
Local scriptsAutomated 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 34 notes
skills/recursive-debugging/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-mode/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-mode/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-mode/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-mode/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-mode/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-mode/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-review-bundle/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-review-bundle/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-router/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-router/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-router/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-router/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-router/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-router/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-tdd/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-tdd/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-tdd/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-training/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/recursive-training/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- No network access
- No hidden or obfuscated text
- 2 instruction override signalsin 1 file: recursive-mode/scripts/recursive-training-phase8-trigger.ps1:16
- 60 executable scriptsin 60 files: recursive-mode/scripts/check-reusable-repo-hygiene.ps1:1 recursive-mode/scripts/check-reusable-repo-hygiene.py:1 recursive-mode/scripts/install-recursive-mode.ps1:1 and 57 more
- 2 references to secretsin 2 files: recursive-mode/scripts/recursive-training-extract.py:85 recursive-mode/scripts/recursive_router_lib.py:558
- No requests to vote in Hot
Show all 64 signals by file
skills/recursive-mode/scripts/check-reusable-repo-hygiene.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/check-reusable-repo-hygiene.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/install-recursive-mode.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/install-recursive-mode.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/install-recursive-mode.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/recursive-mode/scripts/lint-recursive-run.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/lint-recursive-run.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-closeout.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-closeout.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-init.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-init.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-lock.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-lock.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-review-bundle.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-review-bundle.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-router-cli-configure.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-router-cli-configure.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-router-cli-init.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-router-cli-init.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-router-cli-invoke.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-router-cli-invoke.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-router-cli-probe.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-router-cli-probe.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-router-cli-resolve.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-router-cli-resolve.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-router-cli-validate.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-router-cli-validate.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-router-configure.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-router-configure.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-router-init.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-router-init.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-router-invoke.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-router-invoke.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-router-probe.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-router-probe.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-router-resolve.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-router-resolve.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-router-validate.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-router-validate.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-status.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-status.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-subagent-action.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-subagent-action.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-training-extract.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-training-extract.py
skills/recursive-mode/scripts/recursive-training-grpo.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-training-grpo.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-training-loader.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-training-loader.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-training-mcp.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-training-mcp.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-training-phase8-trigger.ps1
skills/recursive-mode/scripts/recursive-training-phase8-trigger.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive-training-sync.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/recursive-training-sync.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive_phase_rules.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive_router_cli_lib.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/recursive-mode/scripts/recursive_router_lib.py
skills/recursive-mode/scripts/verify-locks.ps1
- Executable scriptline 1
Executable file
skills/recursive-mode/scripts/verify-locks.py
- Executable scriptline 1
#!/usr/bin/env python3
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: 64 facts
- Executable script in code of a file that runsrecursive-mode/scripts/check-reusable-repo-hygiene.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/check-reusable-repo-hygiene.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/install-recursive-mode.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/install-recursive-mode.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/install-recursive-mode.sh:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/lint-recursive-run.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/lint-recursive-run.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-closeout.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-closeout.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-init.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-init.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-lock.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-lock.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-review-bundle.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-review-bundle.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-cli-configure.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-cli-configure.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-cli-init.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-cli-init.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-cli-invoke.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-cli-invoke.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-cli-probe.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-cli-probe.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-cli-resolve.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-cli-resolve.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-cli-validate.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-cli-validate.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-configure.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-configure.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-init.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-init.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-invoke.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-invoke.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-probe.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-probe.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-resolve.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-resolve.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-validate.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-router-validate.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-status.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-status.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-subagent-action.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-subagent-action.py:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-training-extract.ps1:1High confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-training-extract.py:1High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuerecursive-mode/scripts/recursive-training-extract.py:85Low confidence
- Executable script in a comment of a file that runsrecursive-mode/scripts/recursive-training-grpo.ps1:1Low confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-training-grpo.py:1High confidence
- Executable script in a comment of a file that runsrecursive-mode/scripts/recursive-training-loader.ps1:1Low confidence
- Executable script in code of a file that runsrecursive-mode/scripts/recursive-training-loader.py:1High confidence
and 14 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/recursive-debugging/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest .codex/AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/recursive-debugging/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/recursive-debugging/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/recursive-debugging/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/recursive-debugging/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.