try-works/role-model / .agents/skills/recursive-mode
recursive-mode
UnverifiedRepository 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.
docs/templates/commands/recursive-status.md
View on GitHub# recursive-status (prompt template)
> Paste this into chat if your agent does not support custom slash commands.
## Usage Pattern
```text
Check recursive-mode status: [run-id]
```
## Script (Recommended)
```powershell
python "<SKILL_DIR>/scripts/recursive-status.py" --repo-root . --run-id "<run-id>"
python "<SKILL_DIR>/scripts/recursive-status.py" --repo-root .
python3 "<SKILL_DIR>/scripts/recursive-status.py" --repo-root . --run-id "<run-id>"
powershell -ExecutionPolicy Bypass -File "<SKILL_DIR>/scripts/recursive-status.ps1" -RepoRoot . -RunId "<run-id>"
pwsh -NoProfile -File "<SKILL_DIR>/scripts/recursive-status.ps1" -RepoRoot . -RunId "<run-id>"
```
## What It Shows
- Current phase and lock state
- Audit blockers for the active phase
- Workflow profile
- Lock-chain status
- Evidence directory summary
- Phase-scoped diff-audit readiness and next steps through Phase 8
- Phase 3 TDD blockers such as missing RED/GREEN evidence or an invalid pragmatic exception
- Phase 3.5 review-bundle blockers such as missing `Review Bundle Path` or a bundle file that does not exist
- Phase 5 QA-mode blockers such as missing human sign-off or missing agent execution evidence
## Example Output Shape
```text
Recursive Run: <run-id>
===================================
Workflow Profile: recursive-mode-audit-v2
Phase Status:
Phase 0 (Requirements) [LOCKED]
Phase 0 (Worktree) [LOCKED]
Phase 1 (AS-IS) [LOCKED]
Phase 2 (TO-BE Plan) [DRAFT]
Phase 8 (Memory) [PENDING]
Current Phase: 2 (TO-BE Plan)
Status: DRAFT
```
## Implementation
1. Scan `/.recursive/run/<run-id>/`
2. Check each artifact for existence, lock status, audit status, and gate status
3. Determine the current active phase
4. Print next-step guidance using the recursive-mode path layout
5. Attribute diff blockers to the phase that owns them instead of retroactively blaming earlier locked phases for late control-plane or memory files
6. For Phase 3.5, report missing or invalid `Review Bundle Path` before lock time
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |