harness-engineering: Instructions file for Claude Code

AGENTS.md

harness-engineering AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from Intense-Visions/harness-engineering. It costs 24,734 tokens per session, scanned A, original, MIT.

A project guide that explains the structure, goals, conventions, and current state of a toolkit for software built with coding agents.

In plain words
What is it for?
It is for orienting agents and developers in an agent-first software project, including its packages, skills, templates, and development rules.
Why use it?
It gives coding agents the background they need to work consistently in the repository and follow its design decisions.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: PreToolUse hook event, but also the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

This is Intense-Visions/harness-engineering's own configuration. It tells Claude Code, Codex and OpenCode how to work on harness-engineering itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything harness-engineering configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Intense-Visions/harness-engineering. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Intense-Visions/harness-engineering/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Intense-Visions/harness-engineering

Made for: Claude Code, 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-engineering AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/intense-visions/harness-engineering/agents-md.svg)](https://agentmods.dev/instructions/intense-visions/harness-engineering/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/intense-visions/harness-engineering/agents-md"><img src="https://agentmods.dev/badge/instructions/intense-visions/harness-engineering/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 24,734 This file is loaded in full into every session.
When invoked 24,734 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 5.1 $0.24734 $0.24734
Opus 5 $0.12367 $0.12367
Sonnet 5 $0.04947 $0.04947
Haiku 4.5 $0.02473 $0.02473

Measured 3d ago against content hash 380cc6f566ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

harness-engineering 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 3d 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 · 1,256 lines

How it starts

The opening of the file, as written. The whole thing — 1,256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Engineering: AI Agent Knowledge Map

This is the single source of truth for AI agents working on the Harness Engineering project. It provides essential context about our repository structure, architecture, conventions, and where to find information.

Project Overview

Harness Engineering is a comprehensive toolkit for transitioning from manual coding to agent-first development. We help teams architect software in ways that enable AI agents to execute, maintain, and improve code reliably and autonomously.

Purpose and Goals

  • Create a reusable library and toolkit for agent-first development
  • Establish patterns that make AI-driven development predictable and scalable
  • Document architectural decisions as the single source of truth
  • Enforce constraints mechanically rather than through code review
  • Measure and improve agent autonomy over time

Current Phase

Complete — All core packages (types, core, cli, eslint-plugin, linter-gen, graph, intelligence, dashboard, orchestrator), 741 skills (claude-code, gemini-cli, codex, and cursor), 16 personas, 19 templates, and 3 progressive examples are implemented. The project is in adoption and refinement mode. See examples/ for progressive tutorials.

Strategic Anchor

This repository ships a Strategic Anchor system for projects that adopt harness. The anchor lives at STRATEGY.md in the repo root (peer of README.md) and grounds downstream agent skills with product-level context that the codebase alone cannot supply.

What STRATEGY.md is

A short, durable file with five required sections (Target problem, Our approach, Who it's for, Key metrics, Tracks) plus three optional sections (Milestones, Not working on, Marketing). Frontmatter carries name, last_updated (ISO date), and version. Schema authority lives in packages/types/src/strategy.ts (cross-layer contract) and packages/core/src/strategy/schema.ts (Zod runtime validator). harness validate checks shape when the file exists.

Read the full file on GitHub · 1,256 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. 3d ago First seen · 1,256 lines · 24,734 tokens per session scan A 380cc6f566ff

Subscribe to this mod's changes

harness-engineering AGENTS.md is an instructions file published in the GitHub repository Intense-Visions/harness-engineering (20 stars, last pushed today), licensed MIT. It adds 24,734 tokens to every session, about $0.1237 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 2026-09-03.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 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

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

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

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 · 4,469 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