harness-ai AGENTS.md

harness-ai AGENTS.md is an instructions file for Codex, OpenCode from harness/harness-ai. It costs 2,689 tokens per session, scanned A, original, Apache-2.0.

A project instruction file for harness-ai, a monorepo that packages related AI-coding integrations for several development tools. A monorepo keeps multiple connected packages in one repository.

In plain words
What is it for?
Use it when working on Harness AI plugins, skills, governance hooks, workspace rules, or integrations for Cursor, Claude Code, VS Code, or Gemini CLI.
Why use it?
It gives coding agents the project structure, required Node.js version, repository setup, and contribution rules they need before making changes.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/harness/harness-ai/agents-md
Clone the repo
git clone --depth 1 https://github.com/harness/harness-ai

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for harness-ai AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/harness/harness-ai/agents-md.svg)](https://agentmods.dev/instructions/harness/harness-ai/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/harness/harness-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/harness/harness-ai/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,689 This file is loaded in full into every session.
When invoked 2,689 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02689 $0.02689
Opus 5 $0.01345 $0.01345
Sonnet 5 $0.00538 $0.00538
Haiku 4.5 $0.00269 $0.00269

Measured 4d ago against content hash e3a620d7fadf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harness-ai 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 4d 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.

AGENTS.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Contribution guide for AI coding agents working in this repository. Follows the agents.md specification. Human contributors should treat it as the canonical reference alongside README.md.

Claude Code reads CLAUDE.md, which is a symlink to this file.
Gemini CLI reads GEMINI.md inside extensions/gemini/.
Cursor / Copilot / Codex / Aider read this file directly.

Project overview

harness-ai is a distribution monorepo that packages Harness AI integrations — skills, governance hooks, workspace rules, MCP config — as separate plugins/extensions for each major AI coding environment (Cursor, Claude Code, VS Code + Copilot, Gemini CLI). The Cursor plugin is published to the Cursor Marketplace; the others mirror the same skills surface for their respective platforms.

Dev environment

# Required — Node 22+ for validator scripts (ESM)
node --version     # expect v22.x

# Clone and orient
git clone https://github.com/harness/harness-ai
cd harness-ai

# Skills mirror (upstream — edits happen there, not here)
git clone https://github.com/harness/harness-skills ../harness-skills

No npm install at repo root. Hook scripts under plugins/cursor/scripts/ run with Node stdlib only (no dependencies).

Build & test commands

File-scoped validators — run the closest one to what you changed.

# Everything (VS Code + Claude + Gemini + Cursor)
./scripts/validate.sh

# Cursor plugin deep check (manifest, mcp.json, hooks, frontmatter, skill-dir match)
( cd plugins/cursor && node scripts/validate-plugin.mjs )

# A single hook script — syntax only
node --check plugins/cursor/scripts/check-templates.mjs

# Smoke-test a hook fail-open path (should print {"permission":"allow"})
echo '{"tool_name":"MCP:harness_create","tool_input":{"resource_type":"pipeline","body":{}}}' \
  | env -u HARNESS_API_KEY -u HARNESS_ACCOUNT_ID ./plugins/cursor/scripts/check-templates.mjs

# Skills drift from upstream — must produce no diff after sync
./scripts/sync-skills.sh ../harness-skills
git diff --stat plugins/*/skills/

Read the full file on GitHub · 171 lines

Changes

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.

  1. 4d ago First seen · 171 lines · 2,689 tokens per session scan A e3a620d7fadf

Subscribe to this mod's changes

harness-ai AGENTS.md is an instructions file published in the GitHub repository harness/harness-ai (19 stars, last pushed 13d ago), licensed Apache-2.0. It adds 2,689 tokens to every session, about $0.0134 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 2026-08-30.

Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens