harness-eval

Evaluate a repo agent harness (AGENTS.md, rules, skills, skill refs) for broken paths/commands, redundant instructions, and usefulness using a stack-agnostic dual-judge protocol with planted traps. HIGH PRIORITY questionnaires at top: Q1 optional docs, Q2 B/C budget before Track A (certainty/tokens). A always runs after Q2; B/C opt-in. ADRs/RFCs excluded from T2. Mixed apply uses 11-mixed-apply.md (KEEP/CUT). Use when the user says harness eval, harness-eval, harness debug, audit AGENTS.md, audit skills/rules, instruction audit, redundancy of agent instructions, usefulness of skills, Ship/Review/Hold/Slim/Keep-core for harness, or wants Track A/B/C harness evaluation. Do NOT use for harness setup or init, feature spec-driven work (tlc-spec-driven), or applying Ship/Slim trims unless the user explicitly asks after the report.

• SKILL.md15,589 bytes
• references/GLOSSARY.md3,825 bytes
• references/PROTOCOL.md11,425 bytes
• references/claims.schema.json704 bytes
• references/judge-prompts.md6,276 bytes
• scripts/doc_scope.py7,176 bytes
• scripts/inventory_extract.py30,498 bytes
• scripts/merge_agreement.py6,014 bytes
• scripts/merge_usefulness.py16,769 bytes
• scripts/slim_fanin.py7,108 bytes
• scripts/surfaces_extract.py8,195 bytes
• scripts/track_a_correctness.py23,284 bytes