experience-review

Codex compatibility note:

• Invoke $skill-name: load the registered .agents/skills/<name>/SKILL.md and execute it with Codex tools; no separate Skill tool or Claude mode switch is needed. When a workflow step or another skill names a skill, read that file in full yourself (every line, with no line limit; in parts only when output is cut off): a skill whose implicit invocation is off is never loaded for you. Author .claude/**; mirrors are generated.
• Track steps before execution and keep progress/evidence current. Explicit skill requests execute their protocol. Use the native question tool for required questions.
• Map foreign tool names to available host capabilities. A name mismatch needs no approval; an actually unavailable required capability stops with its step/evidence and a user question before adaptation.
• Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.
• Preserve protocol order unless the user approves a deviation. Workflows use $start-workflow: gates stay fixed; other steps may flex with logged reasons and evidence.

Quick Summary

Review modes: For review/audit work, standalone defaults to --review-only (--report-only alias); --fix-loop enables review → validate → authorized fix → fresh re-review, default cap 3. --fix-loop --loop-owner=caller returns a read-only pass to the caller that owns fixes/re-review. Create triage, review, validation and re-review todo tasks first; apply the carried review-policy contract for LOW deferral and user-approved bounded extensions. Non-review modes and terminal findings validation keep their own dispatch.

Goal: Exercise the real interface and inspect evidence so acceptance decisions reflect observed behavior.

Summary: Resolve intent → plan evidence/capability → start, instrument and exercise → inspect/judge → repair/re-exercise within budget → compare, tear down and hand off. Keep observations, judgments and human acceptance separate.

Key Rules:

• --rounds=N: integers 0–3; review-only defaults to 0, standalone --fix-loop defaults to 3. A numeric budget never grants repair authority; caller-owned passes stay read-only. State mode and budget before observation.
• Keep the evidence matrix and expectations intact; only BLOCKING defects open repair rounds.
• A clean review recommends acceptance; explicit owner acceptance is required before promoting any baseline.