ai-harness: Instructions file for Claude Code

CLAUDE.md

ai-harness CLAUDE.md is an instructions file for Claude Code from samartomar/ai-harness. It costs 1,359 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Claude working on ai-harness. They explain the difference between the ai-harness source checkout and aih, the installed runtime product, and point to the full project rules.

In plain words
What is it for?
Use them when Claude starts work on ai-harness, especially for project vocabulary, rule routing, tool selection, and keeping source-tree development separate from runtime use.
Why use it?
They prevent Claude from confusing development files with the product that users run, a distinction that affects where changes and checks belong.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is samartomar/ai-harness's own configuration. It tells Claude Code how to work on ai-harness 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 ai-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to samartomar/ai-harness. 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/samartomar/ai-harness/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/samartomar/ai-harness

Made for: Claude Code.

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 ai-harness CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/samartomar/ai-harness/claude-md.svg)](https://agentmods.dev/instructions/samartomar/ai-harness/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/samartomar/ai-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/samartomar/ai-harness/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,359 This file is loaded in full into every session.
When invoked 1,359 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01359 $0.01359
Opus 5 $0.00679 $0.00679
Sonnet 5 $0.00272 $0.00272
Haiku 4.5 $0.00136 $0.00136

Measured yesterday against content hash c146b6eae0e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ai-harness CLAUDE.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 yesterday.

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.

CLAUDE.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ai-harness — Claude bootloader

This file is not the full rulebook. It is the Claude entry point; canonical guidance lives in ai-coding/ (start at RULE_ROUTER.md). The shared block below is a manual self-hosting mirror of ai-coding/adapters/_shared-canonical-block.md; AIH must never regenerate it in this checkout.

Claude auto-loads only this bootloader — the shared block below carries the essentials and routes to the full canon. Full Claude notes: ai-coding/adapters/claude.md.

Repo-specific tool routing: before non-trivial repository work, read ai-coding/rules/repo-ai-tools.md. It overrides generic tool-selection guidance in the shared block below.

Never run AIH against this checkout. Product behavior must use temporary fixture roots in tests; repository-owned direct development checks may inspect this tree.

Vocabulary — two different things

ai-harness (or aih-harness) is this checkout: the source tree, local development on it. aih is the runtime: the shipped product a user installs and runs. Keep them apart in every sentence you write; collapsing them is how "never run AIH against this checkout" gets misread.

ECC and Superpowers are third party to the runtime. aih records their components with provenance — repository, pinned commit, path — and ECC or Superpowers install and run them. A pin on a third-party item is provenance, not a gate. Never describe third-party inventory as unsupported, blocked, fenced, or unable to become effective: aih is not withholding it, aih simply does not install it. Reserve unsupported and blocked for items where an aih-owned gate actually fails — which is aih's own MCP controls, hooks, and custom candidates, not someone else's catalog. Even then, the gate is a label and a next route on a selectable row, never a control-less row: the administrator can always record requested intent from the main window, and the gate holds at export and at target evaluation (owner decision 2026-09-04, issue #971).

Read the full file on GitHub · 108 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. yesterday Changed · +3 lines · +69 tokens per session c146b6eae0e4
  2. 8d ago First seen · 105 lines · 1,290 tokens per session scan A 0b1d9b2d860f

Subscribe to this mod's changes

ai-harness CLAUDE.md is an instructions file published in the GitHub repository samartomar/ai-harness (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,359 tokens to every session, about $0.0068 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.

Related

Other instructions, from other repositories

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 · 5,153 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

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

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

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

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