harness CLAUDE.md

harness CLAUDE.md is an instructions file for coding agents from heba-ramdan/harness. It costs 256 tokens per session, scanned A, original, MIT.

A set of instructions for running and understanding the Masters Of AI Harness, a TypeScript command-line application built on the Claude Agent SDK.

In plain words
What is it for?
Use it to orient yourself in the codebase, list available agents, run the application, or start it inside a sandbox.
Why use it?
It gives contributors a quick map of the project’s entry point, agent loading, tools, interface, configuration, and local commands.

Instructions file

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/heba-ramdan/harness/claude-md
Clone the repo
git clone --depth 1 https://github.com/heba-ramdan/harness

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 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/heba-ramdan/harness/claude-md.svg)](https://agentmods.dev/instructions/heba-ramdan/harness/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/heba-ramdan/harness/claude-md"><img src="https://agentmods.dev/badge/instructions/heba-ramdan/harness/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 256 This file is loaded in full into every session.
When invoked 256 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 $0.00256 $0.00256
Opus 5 $0.00128 $0.00128
Sonnet 5 $0.00051 $0.00051
Haiku 4.5 $0.00026 $0.00026

Measured 5d ago against content hash 9864e22188a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 5d 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.

CLAUDE.md · 29 lines

What it actually says

Masters Of AI Harness

  • DESIGN.md — overview with links to docs/
  • docs/ — architecture, agents, tools, configuration, sandbox, design decisions

Quick Orientation

Standalone agent runtime built on top of the Claude Agent SDK.

Reads agent definition files (IDENTITY.md) directly. Connects to a model, provides MCP tools, handles I/O via React/Ink TUI.

  • TypeScript, runs via tsx (no build step)
  • Entry: bin/mastersof-ai.jssrc/index.tsx
  • Agent loading: src/agent-context.tssrc/agent.ts
  • Tools: src/tools/ — in-process MCP servers, one per domain
  • TUI: src/components/ — React/Ink (DO NOT TOUCH unless broken)
  • Config: ~/.mastersof-ai/config.yaml

Running Locally

npx tsx bin/mastersof-ai.js:
npx tsx bin/mastersof-ai.js --agent researcher
npx tsx bin/mastersof-ai.js --agent researcher --sandbox # Run in a bubblewrap sandbox
npx tsx bin/mastersof-ai.js --list-agents
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. 5d ago First seen · 29 lines · 256 tokens per session scan A 9864e22188a1

Subscribe to this mod's changes

harness CLAUDE.md is an instructions file published in the GitHub repository heba-ramdan/harness (1 stars, last pushed 2d ago), licensed MIT. It adds 256 tokens to every session, about $0.0013 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

SeekMoney-ai CLAUDE.md

Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.

zykooooooooo/SeekMoney-ai · 2,178 tokens

sentry-instrumentation AGENTS.md

Instructions for tortastudios/sentry-instrumentation, covering agents guide — sentry-instrumentation, what this repo is, this repo has no "skill registry", if you're a codex agent asked to install this skill and skill-enable block (copy into consumer agents.md).

tortastudios/sentry-instrumentation · 1,038 tokens

Cerebro AGENTS.md

Instructions for AgenticFirst/Cerebro, covering cerebro — agent context, read before touching integrations, project layout, conventions a fresh agent would otherwise miss and running locally.

AgenticFirst/Cerebro · 1,287 tokens

critical-thinking AGENTS.md

Instructions for Johna2an/critical-thinking, covering agents.md, repo map, install (for a user asking "should i install this?"), working in this repo and running an eval round.

Johna2an/critical-thinking · 731 tokens

idd-skill idd-resume.instructions.md

Instructions for kurone-kito/idd-skill, covering idd — resume phase, required inputs, step 0 — route classifier, operator-present release and step 1 — identify claim state.

kurone-kito/idd-skill · 3,747 tokens

hometax-doum AGENTS.md

AGENTS.md instructions for lbiz-partners/hometax-doum, covering claude.md — hometax-doum 개발 규칙 (하네스와 쌍), 규칙 ↔ 강제 장치 and 운용 메모.

lbiz-partners/hometax-doum · 1,202 tokens