| name | adaptive-harness |
| description | Use this skill when auditing, simplifying, benchmarking, or refactoring an AI/agent project harness, including CLAUDE.md, AGENTS.md, slash commands, skills, subagents, hooks, tool routing, scheduled reviews, AI-review reports, benchmark scaffolds, and rolling harness maintenance. Not for ordinary code review of application code (use code-review) or for running the method-harness-compiler project (use the root harness ladder). |
| id | SKILL-adaptive-harness |
| layer | entry |
| purpose | Skill-runtime adapter for the adaptive harness system - maps the 9 review modes onto the two deterministic runners plus the semantic checklists, under the report-only / patch-proposal safety posture; linkage queries go to the grep-history helper. |
| read_when | A skill-aware runtime (Claude Code and similar) invokes adaptive-harness; or when wiring the improvement loop into a new project. |
| depends_on | ["../../../scripts/run_adaptive_harness_review.py","../../../scripts/run_ai_review.py","../../../scripts/grep_history.py","../../../prompts/ai-review-modes.md","../../../docs/ai_review_adaptive_harness_integration.md","../../../schemas/review_report.schema.yaml","../../../schemas/recommendation.schema.yaml"] |
| used_by | ["claude-code-skill-runtime","AGENTS","PROMPT-hermes-router"] |
| tags | ["entrypoint","skill","adaptive-harness","ai-review","report-only"] |
| retrieval_keywords | ["adaptive harness skill","improvement loop","grep history linkage","harness inventory","skill fit review","patch proposal mode","scheduled harness review","ai review integration","harness cleanup"] |
SKILL: adaptive-harness
Relationship to the root SKILL.md: the root file is the repo-level
launcher for working ON the method-harness-compiler project (the L0→L3
ladder). THIS adapter is the skill-aware runtime entry for the adaptive
harness system — the improvement loop that keeps a harness (this repo's or
the operator's global one) reviewed, simplified, and benchmarkable over time.
AI-review is the local reviewer; adaptive-harness runs the harness-shaped
review modes over its findings. One system, shared schemas, two runners.
Cross-run linkage (which findings repeat, which are closed) is answered
on demand by scripts/grep_history.py — the stateful rolling machinery was
retired per REC-20260714-001 after the pre-registered A/B measured no recall
advantage over re-derivation (a B-loses result that shipped to
docs/evidence.md).
The loop you are operating
- Observe — run AI-review (
python scripts/run_ai_review.py --mode <m>)
and, for harness-shaped scans, the adaptive runner modes below. For
cross-run questions: python scripts/grep_history.py --repeats / --open
/ --rec REC-YYYYMMDD-NNN (read-only; append-only history + git log).
- Diagnose — answer the mode's semantic checklist in
prompts/ai-review-modes.md with cited evidence.
- Classify — every finding gets Keep / Simplify / Remove / Replace /
Merge / Cache / Experiment per
schemas/recommendation.schema.yaml.
- Act safely — low-risk docs drift may be edited only when the human
explicitly allowed it THIS session; high-risk (hooks, subagents, prompts,
permissions, settings, CI) ⇒
--mode patch_proposal renders an
apply/rollback sheet and STOPS; uncertain value ⇒ add a case to
benchmarks/harness_cases.yaml (pre-registered, never self-graded).
- Record — findings enter via
--ingest findings.json (validated);
the runner appends JSONL history and renders JSON→MD deterministically.
Never hand-write report numbers.
- Schedule next — the report's
next_review_trigger names the cadence;
scheduled runs stay report-only.
Modes
| Mode | Runner call | Semantic checklist |
|---|
harness_inventory | |
