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/memory/skills/patterns/delegated-verification-and-refresh.md
View on GitHubType: `pattern`
Status: `CURRENT`
Scope: `How the main agent verifies delegated review or audit work before accepting it as lockable evidence.`
Owns-Paths:
Watch-Paths:
- `/.recursive/RECURSIVE.md`
- `/.recursive/memory/skills/SKILLS.md`
- `/.recursive/run/`
Source-Runs:
- `none (generic repository guidance)`
Validated-At-Commit: `generic-repository-guidance`
Last-Validated: `2026-04-09T00:00:00Z`
Tags:
- `skills`
- `subagent`
- `verification`
- `review-bundle`
# Delegated Verification And Refresh
Delegated work is optional helper output, not autonomous authority.
## Main-Agent Acceptance Rules
Before accepting meaningful delegated work, the main agent should verify:
- claimed file impact against the actual diff-owned file set
- claimed artifact reads or updates against files that actually exist
- review-bundle contents against the current reviewed artifact and artifact hash
- requirement, plan, addenda, and prior recursive docs that materially informed acceptance
- whether any post-review repair made the delegated context stale
## Record In The Phase Artifact
When delegated work materially contributes, `## Subagent Contribution Verification` should record:
- `Reviewed Action Records`
- `Main-Agent Verification Performed`
- `Acceptance Decision`
- `Refresh Handling`
- `Repair Performed After Verification`
## Refresh Rule
If repairs materially change the reviewed artifact, changed-file scope, or evidence basis, refresh the review bundle or action record before relying on delegated work for lockable evidence.
## Rejection Rule
If the main agent cannot verify delegated claims against actual files, actual artifacts, and the actual diff scope, reject the delegated result and fall back to self-audit for lockable completion evidence.
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 |