review-work
Post-implementation review orchestrator. Launches 5 parallel background sub-agents: Oracle (goal/constraint verification), Oracle (code quality), Oracle (security), unspecified-high (hands-on QA execution), unspecified-high (context mining from GitHub/git/Slack/Notion). All must pass for review to pass. MUST USE before a PR handoff or when the user explicitly asks to review completed work. Triggers: 'review work', 'review my work', 'review changes', 'QA my work', 'verify implementation', 'check my work', 'validate changes', 'post-implementation review'.
Profile →npx skills add code-yeongyu/oh-my-openagent --skill review-work --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Launches 5 parallel background sub-agents to perform a post-implementation review: goal/constraint verification, code quality, security, hands-on QA execution, and context mining from various sources. All five must pass for the review to pass. Used before PR handoff or when a user asks to review completed work. Triggers include: 'review work', 'review my work', 'review changes', 'QA my work', 'verify implementation', 'check my work', 'validate changes', 'post-implementation review'.
How it works
- Initiate five agents in parallel in background mode. Each agent has a defined role and focus:
- Goal Verifier (Oracle, MAIN) checks if built work matches the original goal and constraints.
- QA Executor (unspecified-high, MAIN) performs hands-on QA execution.
- Code Reviewer (Oracle, MAIN) evaluates code quality.
- Security Auditor (Oracle, SUB) checks for security issues.
- Context Miner (unspecified-high, MAIN) gathers missing context from sources like GitHub, Git, Slack, Notion.
- The orchestration requires all five to pass; a single failure causes overall review failure.
- Phase 0 gathers context (GOAL, CONSTRAINTS, BACKGROUND, CHANGED_FILES, DIFF, FILE_CONTENTS, RUN_COMMAND).
- Phase 1 launches all five agents in one turn with run_in_background=true, passing full prompt context to Oracle agents and autonomous directives to autonomous agents.
When to use it
Use before a PR handoff or when the user explicitly asks to review completed work. Trigger phrases include: 'review work', 'review my work', 'review changes', 'QA my work', 'verify implementation', 'check my work', 'validate changes', 'post-implementation review'.
What it can touch
- Tools declared: claude-code, codex, cursor. The skill instructs agents to spawn sub-agents and pass context; specific tool calls are described in the Codex Harness guidance within the skill.
Caveats
- All five sub-agents must pass for success. If any fails, the review fails. The orchestrator includes a phase for context gathering and a parallel launch, with explicit requirements about background execution and prompt content.
## Codex Harness Tool Compatibility This skill may include examples copied from the OpenCode harness. In Codex, do not call OpenCode-only tools such as `call_omo_agent(...)`, `task(...)`, `background_output(...)`, or `team_*(...)` literally. Translate those examples to Codex native tools: | OpenCode example | Codex tool to use | | --- | --- | | `call_omo_agent(subagent_type="explore", ...)` | `multi_agent_v1.spawn_agent({"message":"TASK: act as an explorer. ...","agent_type":"explorer","fork_context":false})` | | `call_omo_agent(subagent_type="librarian", ...)` | `multi_agent_v1.spawn_agent({"message":"TASK: act as a librarian. ...","agent_type":"librarian","fork_context":false})` | | `task(subagent_type="plan", ...)` | `multi_agent_v1.spawn_agent({"message":"TASK: act as a planning agent. ...","agent_type":"plan","fork_context":false})` | | `task(subagent_type="oracle", ...)` for final verification | `multi_agent_v1.spawn_agent({"message":"TASK: act as a rigorous reviewer. ...","agent_type":"lazycodex-gate-reviewer","fork_context":false})` | | `task(category="...", ...)` for implementation or QA | `multi_agent_v1.spawn_agent({"message":"TASK: act as an implementation or QA worker.
- Codex Harness Tool Compatibility
- Codex Subagent Reliability
- Phase 0: Gather Review Context
- Phase 1: Launch 5 Agents
- Agent 1: Goal & Constraint Verification (Oracle) - MAIN
- Agent 2: QA via App Execution (unspecified-high) - MAIN
- Agent 3: Code Quality Review (Oracle) - MAIN
- Agent 4: Security Review (Oracle) - SUB
- Agent 5: Context Mining (unspecified-high) - MAIN
- Phase 2: Wait & Collect
- Phase 3: Deliver Verdict
git diff --name-only HEAD~1 # or: git diff --name-only main...HEAD git diff HEAD~1 # or: git diff main...HEAD Check package.json -> "scripts.dev" or "scripts.start" Check Makefile -> default target Check docker-compose.yml -> services
What does the review-work skill do?
Post-implementation review orchestrator. Launches 5 parallel background sub-agents: Oracle (goal/constraint verification), Oracle (code quality), Oracle (security), unspecified-high (hands-on QA execution), unspecified-high (context mining from GitHub/git/Slack/Notion). All must pass for review to pass. MUST USE before a PR handoff or when the user explicitly asks to review completed work. Triggers: 'review work', 'review my work', 'review changes', 'QA my work', 'verify implementation', 'check my work', 'validate changes', 'post-implementation review'.
How do I install it?
Run `npx skills add code-yeongyu/oh-my-openagent --skill review-work --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From code-yeongyu/oh-my-openagent, a repository with 67,209 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.