Borrowing it
Nothing to install: this file belongs to paladini/harness-score. 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/paladini/harness-score/main/AGENTS.mdgit clone --depth 1 https://github.com/paladini/harness-scoreWrote 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/paladini/harness-score/agents-md)<a href="https://agentmods.dev/instructions/paladini/harness-score/agents-md"><img src="https://agentmods.dev/badge/instructions/paladini/harness-score/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/paladini/harness-score/agents-md"><img src="https://agentmods.dev/badge/instructions/paladini/harness-score/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 | $0.01189 | $0.01189 |
| Opus 5.5 | $0.00476 | $0.00476 |
| Sonnet 5.5 | $0.00238 | $0.00238 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
harness-score 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 29d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide — harness-score
What this is
A monorepo shipping AI coding harness engineering as a product: a guide
(VitePress → GitHub Pages), the deterministic, harness-agnostic
harness-score CLI, a growing family of thin per-tool plugins under
plugins/ (Cursor is the flagship/most fully-developed target; see
PLUGINS-ROADMAP.md for the others), and a GitHub Action. The repo
dogfoods its own scanner: it must always score L4 (npm run scan).
Layout
packages/cli/— the scanner. TypeScript, ESM, zero runtime deps.packages/cli/src/checks/— one file per dimension (see.cursor/rules/checks.mdc)packages/cli/src/score.ts— the maturity model (levels L0–L4)
docs/— the VitePress guide.docs/guide/measure-and-improve.mdholds the check catalog with one{#<check-id>}anchor per check.plugins/— one directory per tool (cursor/,claude-code/, …), plusshared/holding the single prose source templated into each (npm run plugins:generate, checked bynpm run plugins:sync-check). Root.claude-plugin/marketplace.jsonlists the Claude Code entry.action/— composite GitHub Action wrapping the CLI.fixtures/level-0..4/— sample repos pinned to each maturity level by tests. Changing a check usually changes a fixture.
Project-local agent skill:
.agents/skills/pr-release-audit/SKILL.md— complete PR/release audit, including current official vendor documentation, site/docs parity, release metadata, and explicit contributor credit. Use it for PR and release work; its release-note and attribution gates are mandatory.
Build & test
npm test— builds the CLI (tsup), typecheckspackages/cli/src/and the packaging-level consumer smoke test (packages/cli/test/types/smoke.ts, imports fromdist/, notsrc/), then runs vitest.npm run lint— Biome (lints + checks formatting).npm run scan— self-audit; must report L4.npm run docs:build— builds the guide; must pass (dead links fail it).npm run bench— scan-time benchmark against a synthetic large repo; use it before/after touchingpackages/cli/src/scan.ts.- Tests MUST pass before any commit.
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.
- 29d ago Changed · +5 lines · +83 tokens per session 1dc1db8aad9f
- 1mo ago Changed · +10 lines · +159 tokens per session 4807855992fc
- 1mo ago Changed · +7 lines · +65 tokens per session 6722de2f2bb2
- 2mo ago First seen · 65 lines · 882 tokens per session scan A 4448bac4dee9
harness-score AGENTS.md is an instructions file published in the GitHub repository paladini/harness-score (613 stars, last pushed 2d ago), licensed MIT. It adds 1,189 tokens to every session, about $0.0048 per session on Opus 5.5. 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 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.