Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From Harness Score
Runs the deterministic harness-score scanner on the repository and presents a maturity audit with level, score, dimension breakdown, and top failed checks.
How this command is triggered — by the user, by Claude, or both
Slash command
/harness-score:harness-auditThe summary Claude sees in its command listing — used to decide when to auto-load this command
# /harness-audit
Audit this repository's AI harness maturity. Follow these steps exactly:
1. Run the deterministic scanner from the workspace root:
Do not analyze the repository yourself — the scanner's output is the
audit. It is fully deterministic (filesystem checks only, no AI, no
network), so its numbers are reproducible facts.
2. Present the results to the user:
- The maturity level (`level.index`, `level.name`) and total score,
with one sentence of interpretation.
- A compact table of the six dimensions with their percentages.
- **The top 3 failed check...Audit this repository's AI harness maturity. Follow these steps exactly:
Run the deterministic scanner from the workspace root:
npx -y harness-score . --json
Do not analyze the repository yourself — the scanner's output is the audit. It is fully deterministic (filesystem checks only, no AI, no network), so its numbers are reproducible facts.
Present the results to the user:
level.index, level.name) and total score,
with one sentence of interpretation.checks[] where passed is
false, sorted by points descending): for each, give the check id,
what is missing (evidence), the concrete fix (remediation), and the
guide link (docsUrl).level.nextLevelGaps is non-empty, state exactly what blocks the
next level.End by offering: "Want me to fix any of these? I can create the missing harness files following the guide's recipes." If the user accepts, use the harness-engineering skill.
If npx fails (offline/registry blocked), say so and suggest installing the
CLI locally with npm i -D harness-score; never substitute your own
estimate for the scanner's output.
npx claudepluginhub paladini/harness-score --plugin harness-score/harness-auditRuns a deterministic audit of a repository's harness configuration, producing a prioritized scorecard across 7 categories with specific failed checks and actionable recommendations. Also supports scoped audits for hooks, skills, commands, or agents.
/harness-auditRuns a deterministic repository harness audit with optional scope, format, and root path, producing a prioritized scorecard with category scores, failed checks, and top actions.
/harness-auditRuns a deterministic repository harness audit across configurable scopes (repo, hooks, skills, commands, agents) and returns a prioritized scorecard with 7 fixed scoring categories.
/harness-auditAudits the repository against the session-orchestrator harness rubric, reporting overall band (healthy/warn/critical), numeric score, and any categories scoring below 7.
/assessScans a repository for AI literacy evidence, asks clarifying questions, produces a timestamped assessment, applies habitat fixes, recommends workflow changes, and adds a literacy badge to the README.
/quickPerforms quick checklist-based harness evaluation on the current project, producing a score (~30s).