Hom Output Checker — Project Management agent for Claude Code
Formats and double-checks the text of a code review or code check in a fresh context, with no file tools.
How to install Hom Output Checker
Installs to ~/.claude/agents/homoantropos-skills-hom-output-checker.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/homoantropos/skills/HEAD/agents/hom-output-checker.md -o ~/.claude/agents/homoantropos-skills-hom-output-checker.md Restart Claude Code, or start a new session, for it to be picked up.
What Hom Output Checker does
name: hom-output-checker description: Formats and double-checks the text of a code review or code check in a fresh context, with no file tools. Pass it the full results, the task and the scope. Never reviews code itself. skills:
- hom-output-formatting
- hom-human-readable disallowedTools: Read, Grep, Glob, Bash, Edit, Write, WebFetch, WebSearch
You receive the text results of a code review or a code check, produced by someone else.
Follow the hom-output-formatting skill exactly, w
Alternatives in Project Management
- Agent Evaluator — Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, concisen 243.5k ★
- Convention Checker — SAGE convention checker — verify recently changed files against convention docs declared in the project profil 109 ★
- Grainulator — Autonomous research sprint subagent 87 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Env Checker
Use when requirements-orchestrator needs the repo's OS/project requirements verified against requirements.json
Ue Build Verifier
Use to compile the project and/or run automation tests headless and report results. Trigger after code changes
Unity Compat Checker
Detect Unity, Java, MaxSDK, Android API, Gradle, and scripting backend (IL2CPP/Mono) versions in a Unity proje
Judgment Builder
Builds one scoped task where a wrong build could still pass every check (judgment work). Spawned by the build-
Get Me Result PM
PM agent for get-me-result. Takes a task that needs N separate results, runs worker agents, verifies their out
Docs Warden
Cross-surface consistency checker for genai_incidents. Use PROACTIVELY after any merged task that changes coun
Related Skills
V Collect
Re-run the collect + scope-gate + review tail of a Compound V run by run-id. Normalizes each job's output into
Five Bugs
A 10-minute smoke test for AI coding agents. Five seeded Python bugs, one checker the agent sees and one it ne
Clear Rewrite
Rewrite text to pass CLEAR-100. Plain words, human voice, real structure, no filler. Runs the checker in a loo