zernie/vigiles

Verify the references in your agent instruction files (CLAUDE.md/AGENTS.md) and compile typed specs — in CI.

Trust Signals

Scorecard Score: not yet scored
Maintenance Recency: Stale
License: None

Inputs

name	description	required	default
command	Which vigiles command to run: 'lint' (verify references + integrity + coverage), 'compile' (specs → markdown), or 'eval-check' (verify committed eval locks against current inputs — the staleness gate; runs NO model, so it is the CI-safe half of evals you produce locally with `vigiles eval --update`).	no	lint
paths	Comma- or space-separated paths to operate on (.md files for lint, .spec.ts files for compile). Auto-discovers when empty.	no	""
version	Version of the vigiles npm package to run (e.g. '1', '1.2.3', 'latest'). Use 'local' to run the action's own checkout — for dogfooding via `uses: ./` in this repo's CI.	no	latest
max-rules	Maximum number of rules per spec file (maps to the CLI's --max-rules).	no	""
catalog-only	Only check that linter rules exist; skip config-enabled checks (maps to the CLI's --catalog-only). 'true' or 'false'.	no	false
working-directory	Directory to run vigiles in.	no	.
comment	On pull_request events, post/update a sticky PR comment with the result ('true' or 'false'). Requires `pull-requests: write`.	no	true
capability-diff	On pull_request events, compare the agent's capability surface (the subagents' tool/effect blast radius) against the PR base and fold the diff into the sticky comment (maps to `audit --capability-diff`). Requires `fetch-depth: 0` on checkout so the base commit is present. 'true' or 'false'.	no	false
fail-on-widen	With capability-diff, fail the run when the PR WIDENS the blast radius (maps to the CLI's --fail-on-widen). 'true' or 'false'.	no	false
github-token	Token used to post the PR comment. Defaults to the workflow token.	no	${{ github.token }}

Outputs

name	description
valid	'true' if vigiles passed (exit 0), 'false' otherwise.