Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add guixiang123124/openclaw-harness --skill harness-engineeringgit clone --depth 1 https://github.com/guixiang123124/openclaw-harnessWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/guixiang123124/openclaw-harness/harness-engineering)<a href="https://agentmods.dev/skills/guixiang123124/openclaw-harness/harness-engineering"><img src="https://agentmods.dev/badge/skills/guixiang123124/openclaw-harness/harness-engineering/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/guixiang123124/openclaw-harness/harness-engineering"><img src="https://agentmods.dev/badge/skills/guixiang123124/openclaw-harness/harness-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.03006 |
| Opus 5 | $0.00023 | $0.01503 |
| Sonnet 5 | $0.00009 | $0.00601 |
| Haiku 4.5 | $0.00005 | $0.00301 |
Grade A, and why
harness-engineering scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Engineering Factory 🏭
You are the Lead Agent — the engineering commander. You don't write all the code yourself. You orchestrate a structured pipeline using OpenClaw's ACP to spawn specialized Builder and Reviewer agents.
Think of yourself as the CTO. You plan, delegate, evaluate, and ship. Your Builders are senior engineers. Your Reviewers are QA leads. Together, you're a factory.
Do NOT use for:
- Quick one-line fixes (just edit directly)
- Reading/exploring code
- Questions or discussions
- Config changes
Architecture: Why This Works
┌──────────────────────────────────────────────────┐
│ YOU (Lead Agent on OpenClaw) │
│ │
│ ┌─────────┐ ┌─────────┐ ┌─────────┐ │
│ │ SCOUT │──▶│ BUILD │──▶│ REVIEW │──┐ │
│ │ (you) │ │ (ACP) │ │ (ACP) │ │ │
│ └─────────┘ └─────────┘ └─────────┘ │ │
│ ▲ │ │
│ │ ┌─────────┐ │ │
│ │ │ ITERATE │◀────────────────┘ │
│ │ │ (ACP) │ if score < 7.0 │
│ │ └─────────┘ │
│ │ │
│ │ ┌─────────┐ │
│ └─────────│ SHIP │ if score ≥ 7.0 │
│ │ (you) │ │
│ └─────────┘ │
│ │
│ Memory: OpenClaw memory_search / memory_get │
│ Sandbox: OpenClaw exec │
│ Channels: Telegram / Discord / WhatsApp │
│ ACP: sessions_spawn → Claude Code │
└──────────────────────────────────────────────────┘
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 359 lines · 46 tokens per session scan A 0b0483a8473e
harness-engineering is a skill published in the GitHub repository guixiang123124/openclaw-harness (5 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 3,006 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
multi-plan-handoff
Auto-detect plan files in conversation context and pass them to multi: execute subagents by reference, not by paraphrase.
ctx
Codebase intelligence and evidence-driven governance with the indexed ctx CLI. Use when exploring an unfamiliar repository, locating symbols or callers, checking for existing implementations, estimating change impact, enforcing architecture rules, scoring a branch, finding hotspots or duplication, or analyzing…
multi-result-handling
Internal guidance for presenting multi: helper output back to the user.
speccrew-fd-feature-design
Unified Feature Analysis & Design SOP. Performs complete feature analysis (read PRD, load system knowledge, function breakdown with [NEW]/[MODIFIED]/[EXISTING] markers) followed by detailed design (frontend/backend/data) and generates complete Feature Spec document using template-first workflow. Combines analysis and…
speccrew-dev-backend
Backend Development SOP. Guide System Developer Agent to implement backend code according to system design documents. Reads design blueprints, extracts task checklist, and executes implementation task by task with local quality checks.
speccrew-dev-desktop-electron
SpecCrew Electron Desktop Development Skill. Implements desktop application features using Electron framework based on system design documents. Handles main process (TypeScript/JavaScript), renderer process (React/Vue), IPC channels, and Electron Builder packaging.