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.
git clone --depth 1 https://github.com/NieZhuZhu/ai-harness-doctorWrote 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/commands/niezhuzhu/ai-harness-doctor/harness-eval)<a href="https://agentmods.dev/commands/niezhuzhu/ai-harness-doctor/harness-eval"><img src="https://agentmods.dev/badge/commands/niezhuzhu/ai-harness-doctor/harness-eval/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/commands/niezhuzhu/ai-harness-doctor/harness-eval"><img src="https://agentmods.dev/badge/commands/niezhuzhu/ai-harness-doctor/harness-eval.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 | $0.00009 | $0.00153 |
| Opus 5 | $0.00005 | $0.00077 |
| Sonnet 5 | $0.00002 | $0.00031 |
| Haiku 4.5 | $0.00001 | $0.00015 |
Grade A, and why
harness-eval 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 12d 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.
This is a copy
84% identical to harness-doctor — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Target repo: $ARGUMENTS if provided, otherwise the current working directory.
Locate the installed AI Harness Doctor skill in this order:
<target-repo>/.claude/skills/ai-harness-doctor~/.claude/skills/ai-harness-doctor
Read <skill>/SKILL.md first. Then execute Phase 3 — Efficacy (Eval) only on the target repo, obeying the exact stop condition documented in SKILL.md. Use the deterministic scripts under <skill>/scripts/; do not substitute scripts from the target repo unless they are the installed skill scripts.
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.
- 12d ago First seen · 14 lines · 9 tokens per session scan A 56c39e658552
harness-eval is a command published in the GitHub repository NieZhuZhu/ai-harness-doctor (2 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 153 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 84% identical to harness-doctor, differing in 4 lines, and is treated as a copy.
Other commands, from other repositories
apex-quick
Quick Flow for bounded fixes - the full APEX route with Brainstorm skipped and Plan compressed to one task; Analyze trio, delegated execution, eLicit, Verify, challenger and full sniper always run.
test
Test commit. Use for add tests, update tests, test coverage, unit test, spec.
email-test-suite
../../services/email/email-test-suite.md.
auto-verify
A command for checking a website's front-end user experience with Playwright, a tool that automates web browsers.
ui-snapshot.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
write-skill-test
RED-GREEN-REFACTOR implementation for writing-skills: Baseline testing, minimal skill writing, loophole closure, and full creation checklist.