Borrowing it
Nothing to install: this file belongs to NieZhuZhu/ai-harness-doctor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NieZhuZhu/ai-harness-doctor/main/AGENTS.mdgit 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/instructions/niezhuzhu/ai-harness-doctor/agents-md)<a href="https://agentmods.dev/instructions/niezhuzhu/ai-harness-doctor/agents-md"><img src="https://agentmods.dev/badge/instructions/niezhuzhu/ai-harness-doctor/agents-md/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/instructions/niezhuzhu/ai-harness-doctor/agents-md"><img src="https://agentmods.dev/badge/instructions/niezhuzhu/ai-harness-doctor/agents-md.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 | $0.02190 | $0.02190 |
| Opus 5 | $0.01095 | $0.01095 |
| Sonnet 5 | $0.00438 | $0.00438 |
| Haiku 4.5 | $0.00219 | $0.00219 |
Grade A, and why
ai-harness-doctor AGENTS.md 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 11d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project overview
This repository contains the ai-harness-doctor Claude Code skill. It audits, consolidates, guards, and evaluates AI harness configuration files around a canonical AGENTS.md.
Project structure
SKILL.md— the skill contract and the four-phase workflow (Checkup → Treat → Follow-up → Efficacy).scripts/— deterministic Python engines:scan.py— Phase 0 inventory/security scan, monorepo results, structured applicability, and debt baselines.semantic.py— Phase 0 declaration-vs-code facts for Node, Python, Go, Rust, Java, and Ruby.applicability.py— bounded Claude/Cursor/Copilot applicability; no general YAML.canonicalize.py— Phase 1 merge plan,--draft, tool-stub downgrade, and validation.check_drift.py— Phase 2 root/nested D1–D8 guard, health,--fix, and baselines.explain.py— read-only target-path projection of scan's canonical scope, diagnostic-source, override, and conflict evidence.plugins.py— opt-in deterministic.ai-harness-doctor/rules/*.pyengine; plugin failures becomeERRORfindings instead of crashing.eval_run.py— Phase 3 Efficacy: before/after + matrix eval runner and LLM-as-judge grading.pr_review.py— Phase 2/3 CI helper: combines active scan+drift JSON (root/package/batch) into one attributed GitHub review;--dry-runprints it,--postuses the stdlib REST client.gen_adapters.py— repo-maintenance tool (not shipped in the npm package): regenerates the per-commandadapters/from a single source;--checkgates re-divergence in CI.
bin/cli.js— npm CLI/installer/forwarder;bin/mcp-server.js— MCP stdio;bin/runtime.js— Python resolver;bin/action-run.js/bin/action-report.js— Action argv and SARIF reporting.assets/— templates:assets/AGENTS.template.mdand theassets/guard/suite;references/— progressive-disclosure docs.commands/,adapters/— Claude/Codex/Cursor/Gemini/universal command pointers. Editscripts/gen_adapters.py, then regenerate; do not hand-edit generated adapter flavors.tests/— Python unittest + Node CLI smoke tests;benchmark/— self-benchmark and efficacy eval fixtures.
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.
- 11d ago First seen · 103 lines · 2,190 tokens per session scan A 827e4f8e7c37
ai-harness-doctor AGENTS.md is an instructions file published in the GitHub repository NieZhuZhu/ai-harness-doctor (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,190 tokens to every session, about $0.0110 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 instructions, from other repositories
whichrules copilot-instructions.md
Instructions for z35068037/whichrules, a project described as: See exactly which instructions your AI coding agent receives - and where they conflict.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.