OpenParable
Skip to content
← Back to skills

Agent Md Verify

Testing & Quality
agent-md-verify

Agent Md Verify is an Agent Skill for testing & quality published in the iamfakeguru/agent-md repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Use when finishing work in a repository that has agent-md installed; runs the declared checks, updates memory/progress.md, and reports concrete verification evidence instead of self-grading.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/iamfakeguru/agent-md/blob/HEAD/.agents/skills/agent-md-verify/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/agent-md-verify, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

agent-md Verification

Use this skill before claiming work is complete in an agent-md repository.

  1. Read memory/verify.md and identify the checks required for this task.
  2. Run the project verification commands declared in agent-md.toml when present.
  3. If agent-md.toml is absent, use the repository's existing test/lint/typecheck scripts or the hook heuristics.
  4. For source changes, update memory/progress.md with the completed atomic task and the checks that passed.
  5. If no checks exist, say the work is unverified and add a follow-up item to define checks.
  6. Do not describe code as correct based only on inspection. Provide command output, artifact paths, or reviewer evidence.

Useful helper:

./.agent-md/bin/discover_helpers.sh