Code verifier
Linlin's curated AI agent harness configuration: workflow rules, skills, hooks, plugin recommendations, tooling preferences, and project templates. Loadable into any new project so a fresh /init can pick the relevant subset.
npx -y skills add jajupmochi/agent-harness --skill code-verifierAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Audit whether code, tests, scripts, or reported results are genuine before claiming success. Use before saying tests pass, code works, a script ran, training converged, or results show a conclusion.
SKILL.md
0.8 KB, as published. Nobody here has run it
code-verifier
Read ../general/code-verifier/SKILL.md completely before using this skill.
Codex-specific requirements:
- Treat command output, file contents, and test artifacts as evidence only after inspecting them in the current run.
- Look for fake-run patterns in tests, scripts, and pipelines before trusting green output.
- If the verification scope is narrower than the claim, narrow the claim.
- Surface blockers plainly when required commands cannot run.
- Do not rely on memory, intent, or stale logs as proof.