Runs shared drift-detection engine for /harness-audit and /harness-sync, producing structured reports on convention files, ONBOARDING.md, snapshot staleness, template drift, constraint regressions, reflection patterns, and HARNESS.md status accuracy.
npx claudepluginhub habitat-thinking/ai-literacy-superpowers --plugin ai-literacy-superpowersThis skill uses the workspace's default tool permissions.
The harness audit-engine is the shared drift-detection layer that both
Orchestrates pipeline of 4 skills to check documentation drift, coverage gaps, links, and freshness with convergence-based fixes, producing health report. Use post-refactor, periodic hygiene, or onboarding.
Diagnoses agent harness maturity against 12 principles via file checks and greps, scoring levels (L1-L5) and suggesting setup, audit, or maintenance improvements without modifications.
Audits .claude/ config for cross-references, permissions, inventory drift, model tiers, docs freshness. Auto-fixes issues at high/medium/all severity levels or upgrades with verification and A/B testing.
Share bugs, ideas, or general feedback.
The harness audit-engine is the shared drift-detection layer that both
/harness-audit and /harness-sync invoke. Audit is read-only; sync
uses the same engine to drive its multi-select prompt. This skill
defines the contract — what surfaces are scanned, the drift-report
shape, and the per-finding [auto] / [manual] classification rule.
/harness-audit and /harness-sync are the two callers. Their UX
differs (audit prints, sync prompts), but the underlying findings are
the same.
The engine evaluates every surface or fact that could be out of sync
with HARNESS.md. The current scan covers:
| Category | Finding | Auto-fixable? |
|---|---|---|
| Convention files | .cursor/rules/ matches HARNESS.md | yes — /convention-sync |
| Convention files | .github/copilot-instructions.md matches HARNESS.md | yes — /convention-sync |
| Convention files | .windsurf/rules/ matches HARNESS.md | yes — /convention-sync |
| Onboarding | ONBOARDING.md matches HARNESS.md + AGENTS.md + REFLECTION_LOG.md | manual — /harness-onboarding |
| Observability | Most recent snapshot in observability/snapshots/ is < 30 days old | yes — /harness-health |
| Status section | HARNESS.md Status block matches actual constraint enforcement counts | yes — /harness-audit (audit updates Status as a side-effect) |
| Template currency | <!-- template-version: X --> in HARNESS.md matches installed plugin version | manual — /harness-upgrade |
| Constraint regression | Any constraint marked deterministic whose tool no longer succeeds | manual — /harness-constrain |
| Reflection pattern | Recurring failure pattern in REFLECTION_LOG.md (2+ similar entries, not yet a constraint) | manual — /harness-constrain |
| CI / CD | Constraint scope handled at runtime by harness-enforcer | informational — handled at runtime |
New surfaces added to the engine appear in both commands automatically.
The engine returns a list of findings. Each finding has:
surface — short label (e.g. .cursor/rules/, Snapshot staleness)status — one of drifted, missing, in sync, managed, candidatedetails — short string with the specific evidence (e.g. last: 2026-04-15, HARNESS: 0.31, plugin: 0.34)action_command — the slash command that remediates this finding (e.g. /convention-sync, /harness-upgrade)auto_fixable — true if the action runs without further user judgement; false if the action requires user inputdrifted — file or fact exists but does not match HARNESS.md / reality.missing — file expected but not present.in sync — matches HARNESS.md / reality.managed — handled at runtime by other layers (CI/CD); informational only.candidate — finding that is not strict drift but warrants review (recurring reflection patterns; deferred constraints).A finding is auto_fixable: true only when:
/harness-audit, snapshot creation via /harness-health).Findings that need user input — choosing which constraint to add, deciding whether enforcement should be promoted, deciding when to take an upstream template upgrade — are auto_fixable: false. Sync surfaces them as [manual] rows; selecting them prints the suggested command without writing.
Each caller is responsible for its own UX:
/harness-audit prints the findings in its existing format and updates HARNESS.md Status section./harness-sync builds its drift table from the findings, prompts for selection, and dispatches the action commands.The engine itself does not print or prompt. It returns the findings and exits.
When a new check is added to the engine:
auto_fixable classification using the rule.action_command it maps to./harness-audit and /harness-sync pick up the new finding without further code changes.This is the value of factoring the engine: surface coverage evolves in one place.