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/DECISIONS.md
View on GitHub# DECISIONS.md
## Recursive Run Index
- No run history is intentionally checked into this reusable skill repository.
## Current Working Decisions
- Keep Python as the canonical implementation surface for complex enforcement logic and use PowerShell wrappers where that materially reduces parity drift.
- Treat subagent availability as environment-dependent and require a concrete capability probe before choosing delegated review.
- Treat delegated review as valid only when the bundle and any meaningful subagent work can be verified against actual files, actual recursive artifacts, and the actual diff basis.
- Prefer `mixed` as the documented smoke mode when cross-toolchain parity is desired, while keeping `python` independently runnable in environments without PowerShell.
- Require status-specific evidence fields in `## Requirement Completion Status` so audited artifacts cannot pass on vague prose-only completion claims.
- Treat `/.recursive/memory/skills/` as an optional durable memory surface: retrieve or update specific skill-memory docs only when those docs have been intentionally promoted as reusable repository guidance.
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 | Unverified | 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 |