# Harness

> Automated quality check loops with escalation and fix sub-agents

- Skill: `majiayu000/harness` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add majiayu000/harness`
- Raw SKILL.md: https://api.skillmd.com/api/skills/majiayu000/harness/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: majiayu000 (https://skillmd.com/u/majiayu000)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/majiayu000/harness

---


# Harness

Automated fix loops. Each harness runs a make target, spawns sub-agents to fix failures, commits on success, reverts on exhaustion.

**Pattern:** `.claude/harness/<name>/run` + `fix.prompt.md`

**Escalation:** sonnet:think → opus:think → opus:ultrathink

**History:** Each harness maintains `history.md` for cross-attempt learning. Truncated per-file, accumulates across escalation. Agents append summaries after each attempt so higher-level models can avoid repeating failed approaches.

**CLI:** `.claude/scripts/check-<name>` symlinks to harness run scripts

**Commands:** `/check-<name>` runs the corresponding harness with `--no-spinner`

**Quality:** `quality/run` orchestrates all harnesses in sequence until stable

## Running check-* Skills

When invoking check-* skills via Bash:

- **Timeout:** Use 60 minute timeout (`timeout: 3600000`)
- **Foreground:** Always run in foreground (never use `run_in_background`)
- **Blocking:** No output until completion—do not tail or monitor, just wait
- **Output format:** Structured JSON: `{"ok": true/false, "items": [...]}`