← ClaudeAtlas

orphan-ref-validatorlisted

Detect references to skills, scripts, and counts in structured artifacts (specs, ADRs, eval fixtures, plugin manifests, skill descriptions) that do not match working-tree state. Run as a /build Mandatory Exit Gate to block orphan refs pre-commit instead of paying iteration rounds in /pr-quality:all post-PR.
rjmurillo/ai-agents · ★ 33 · AI & Automation · score 79
Install: claude install-skill rjmurillo/ai-agents
# orphan-ref-validator ## Purpose Scans structured artifacts (specs, ADRs, eval fixtures, plugin manifests, skill descriptions) for references to entities that do not exist in the working tree: - **Skill names** that no longer have a `.claude/skills/<name>/` directory. Emitted as `Finding(kind="skill_name", severity="critical")`. - **Script paths** under `build/scripts/`, `scripts/validation/`, or `scripts/` that are not present on disk. Emitted as `Finding(kind="script_path", severity="critical")`. - **Count claims** in plugin or marketplace manifests. The regex extracts the canonical claim shape (`COUNT_CLAIM_RE` mirrors `build/scripts/validate_marketplace_counts.py:COUNT_PATTERN`), but emission is delegated to that canonical validator. PR1 ships detection only; an opt-in `--enforce-counts` is reserved for PR2 single-plugin enforcement. Per `.claude/rules/canonical-source-mirror.md`, the canonical's YAML-driven per-plugin source-dir resolution and `--fix` path are not duplicated here. Emits findings per the ADR-056 envelope and a final verdict line. Exit code follows ADR-035: `VERDICT: PASS` or `VERDICT: WARN` exits `0`; `VERDICT: CRITICAL_FAIL` exits `1`; configuration or runtime failures emit `VERDICT: ERROR` with `Success: false` and a populated `Error` block (`Code: 2`, `Type: InvalidParams`) and exit `2`. The skill ships with vendored installs. When a target path is not present (for example, `.agents/` is absent), the skill logs INFO and continues; it does not rai