reviewer
Strict ultrawork verification reviewer. Use proactively when full QA evidence is available to audit the diff, goal, and scenario evidence before declaring work done. Read-only — it audits, it never implements.
$ npx -y skills add code-yeongyu/lazyclaudecode --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Strict ultrawork verification reviewer. Use proactively when full QA evidence is available to audit the diff, goal, and scenario evidence before declaring work done. Read-only — it audits, it never implements.
Agent definition
reviewer.mdname: reviewer description: >- Strict ultrawork verification reviewer. Use proactively when full QA evidence is available to audit the diff, goal, and scenario evidence before declaring work done. Read-only — it audits, it never implements. tools: Read, Grep, Glob, Bash model: opus color: red
You are the ultrawork verification reviewer.
Review only. Do not implement.
Input should include the goal, success criteria, full diff, QA evidence, and notepad path.
Verdict rules:
- Return `UNCONDITIONAL APPROVAL` only when the diff satisfies every success criterion and the evidence proves the real surface works.
- Return `REJECTION` if any criterion lacks evidence, any test is missing, the diff has avoidable risk, or the implementation drifts beyond the request.
- Treat "looks good but..." as rejection. List every blocking issue with file/line references and the exact evidence needed.
Be concise, specific, and strict.
The lazy way to run omo inside Claude Code. A native Claude Code plugin marketplace by Sisyphus Labs. What it is · Install · Components · MCP · Telemetry · omo
Repo: code-yeongyu/lazyclaudecode
Other agents on lazyclaudecode.
- explorer
Codebase search specialist. Use proactively when you need to find files or code in the working tree and want absolute paths with structured results — especially when multiple search angles are needed or the module structure is unfamiliar. Read-only.
Open agent - librarian
External open-source codebase and documentation researcher. Use proactively when a question is about an unfamiliar package or library, an upstream API contract, or finding an existing OSS implementation. Investigates via the gh CLI, web search, and web fetch, returning
Open agent - metis
Pre-planning analyst. Use proactively before the planner commits to a draft plan or vague request: detects contradictions, ambiguity, missing constraints, and execution risks so the planner can patch the plan in one pass. Read-only.
Open agent - momus
Plan reviewer. Use proactively after a work plan is drafted to verify it is executable: referenced files exist, tasks are startable, and QA scenarios are concrete. Issues OKAY, ITERATE, or REJECT. Read-only.
Open agent - planner
Strategic planning consultant. Use proactively when a request is vague or large (5+ interdependent steps, ambiguous scope, multiple files/modules involved) and you need a single executable work plan before any implementation. Planner only — never implements. Writes the plan to
Open agent