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.
references/benchmarks/team-capacity-board/prompt-recursive-off.md
View on GitHubImplement the benchmark project in this repository.
Read:
- no controller-authored benchmark docs in the repo for this arm
Rules:
- Do not install or use recursive-mode.
- The benchmark requirements and rubric are provided in this chat prompt only, not in repository docs.
- Keep a benchmark progress log in `benchmark/agent-log.md`.
- Each log entry should include a UTC timestamp, what you tried, issues met, and whether build/test/preview status changed.
- If the controller provides a hint during the benchmark, append it to `benchmark/hints.md` with a UTC timestamp and a short note about what changed afterward.
- If you take screenshots for browser or visual validation, save them under `benchmark/screenshots/` and record the file paths in `benchmark/agent-log.md`.
- If your runtime exposes token or usage metrics, record them in the log; otherwise note that they were unavailable.
- Finish by making the project build, test, and preview locally when possible.
- In your final response, summarize completion status, build status, test status, preview status, screenshot paths if any, and any remaining gaps.
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: 471k | 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 |