init

sliday/harn

Scaffold a complete harness for the current project — AGENTS.md, hooks, guardrails. Use when starting a new project or hardening an existing one. Triggers: /harn:init, 'set up harness', 'scaffold guardrails', 'create AGENTS.md'

2026-04-075

agents-md

sliday/harn

Build or rebuild AGENTS.md with progressive disclosure. Use when: /harn:agents-md, 'create AGENTS.md', 'update agent instructions', 'too many instructions'

2026-04-075

checkpoint

sliday/harn

Scaffold resume artifacts (LEARNED.md, CHECKPOINT.json) for long-running sessions. Triggers: /harn:checkpoint, 'resume artifacts', 'checkpoint', 'session recovery', 'LEARNED.md'

2026-04-075

context-monitor

sliday/harn

Generate context monitoring and backpressure hooks. Triggers: /harn:context, 'context monitoring', 'backpressure', 'context budget', 'attention budget', 'context rot'

2026-04-075

quality-gate

sliday/harn

Generate or update the quality gate Stop hook. Use when: /harn:quality-gate, 'set up type checking', 'add quality gate', 'stop hook'

2026-04-075

security-guard

sliday/harn

Generate or update security guardrail hooks. Use when: /harn:guard, 'update security rules', 'block dangerous commands', 'add guardrail'

2026-04-075

name	car-analyzer
description	Audit project harness against the CAR framework. Use when: /harn:analyze, 'audit harness', 'check CAR', 'harness health', 'how good is my harness'

name	car-analyzer
description	Audit project harness against the CAR framework. Use when: /harn:analyze, 'audit harness', 'check CAR', 'harness health', 'how good is my harness'

car-analyzer

Reference: https://harn.app/kb/evals.html — "Deterministic verifiers over LLM-as-judge"

CAR Framework Analyzer

CAR Scorecard (check each item, tally points)

Control Layer (40 points)

Agency Layer (25 points)

Runtime Layer (35 points)

Scoring

Remediation Guide

Reference: https://harn.app/kb/evals.html — "Deterministic verifiers over LLM-as-judge"

CAR Framework Analyzer

CAR Scorecard (check each item, tally points)

Control Layer (40 points)

Agency Layer (25 points)

Runtime Layer (35 points)

Scoring

Remediation Guide

car-analyzer

Reference: https://harn.app/kb/evals.html — "Deterministic verifiers over LLM-as-judge"

CAR Framework Analyzer

CAR Scorecard (check each item, tally points)

Control Layer (40 points)

Agency Layer (25 points)

Runtime Layer (35 points)

Scoring

Remediation Guide

Mais deste repositório

Mais deste repositório

Reference: https://harn.app/kb/evals.html — "Deterministic verifiers over LLM-as-judge"

CAR Framework Analyzer

CAR Scorecard (check each item, tally points)

Control Layer (40 points)

Agency Layer (25 points)

Runtime Layer (35 points)

Scoring

Remediation Guide