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.
.recursive/STATE.md
View on GitHub# STATE.md
## Current State
- The repository now uses `/.recursive/RECURSIVE.md` as the single canonical workflow specification.
- The workflow profile in active use is `recursive-mode-audit-v2`.
- Executable diff-basis normalization is implemented across lint, status, review-bundle generation, and lock-time validation.
- Audited phases now require status-specific, machine-checkable `Requirement Completion Status` entries rather than traceability-only completion claims.
- Delegated review is grounded by canonical review bundles, prior recursive evidence, and durable subagent action records under `/.recursive/run/<run-id>/subagents/`, with explicit main-agent verification recorded in the phase artifact.
- Skill memory is available as an optional durable part of the memory plane via `/.recursive/memory/skills/`, with generic router/index support and category directories for intentionally promoted reusable guidance.
- The maintained smoke harness lives in `scripts/test-recursive-mode-smoke.py` and `scripts/test-recursive-mode-smoke.ps1`, supports `python`, `powershell`, and `mixed` toolchain modes, and records lazy PowerShell fallback/skip behavior.
- `scripts/install-recursive-mode.py` and `scripts/install-recursive-mode.ps1` scaffold the skill-memory router and category directories, and late closeout uses `scripts/recursive-closeout.py` / `.ps1` to seed audited Phase 4-8 receipts with machine-checkable requirement fields.
## Notes
- Reusable workflow docs in this repository should remain generic. Do not check in self-run control-plane history, run artifacts, or run-derived memory unless that is an intentional product requirement.
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: 469k | 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: 321k | 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: 321k | 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: 321k | Updated | Claude CodeCodex | Verified | Install |