Review self
Independently review and simplify the agent's current implementation, working-tree changes, or pull request; enforce KISS and repository SSOT rules, fix actionable in-scope gaps, rerun relevant verification, and recheck at the user-requested interval (five minutes by default) until stable or genuinely blocked. Use when the user says "review-self", asks Claude to review its own changes, requests a self-review loop, or wants current work monitored for new issues after implementation.From its SKILL.md
npx -y skills add hyodotdev/openiap --skill review-selfAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
1.7 KB, as published. Nobody here has run it
Review Self (Claude Code)
The canonical loop definition lives in .codex/skills/review-self/SKILL.md.
Read it and follow every section — authority and scope preservation, target
establishment, the KISS/SSOT review round, related OpenIAP workflows, the
requested-interval recheck contract, safe stopping conditions, and per-round
communication are agent-agnostic and apply as written.
Claude Code Notes
- Where the canonical file routes through
$openiap-workflows, read the matching.claude/commands/*.mdfile directly (or use the.claude/skills/openiap-workflowsskill). - For interval rechecks, use Claude's real wake-up mechanism for the current
surface (for example a scheduled reminder / wake-up tool in Cowork or the
Agent SDK). Honor the user's interval, defaulting to five minutes. If no such
mechanism is available in the current session, complete the current round and
report that automatic re-entry could not be scheduled — never emulate the
loop with
sleep,while true, or an abandoned background process. - Use read-only subagents (Task/Agent tool with an Explore-style agent) for independent review lenses on large or cross-cutting diffs.