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.
npx agentmods add instructions/adrielp/ai-engineering-harness/claude-mdgit clone --depth 1 https://github.com/adrielp/ai-engineering-harnessWrote 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/adrielp/ai-engineering-harness/claude-md)<a href="https://agentmods.dev/instructions/adrielp/ai-engineering-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/adrielp/ai-engineering-harness/claude-md.svg" alt="Measured on agentmods" 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 | $0.01068 | $0.01068 |
| Opus 5 | $0.00534 | $0.00534 |
| Sonnet 5 | $0.00214 | $0.00214 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
ai-engineering-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 6d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is an AI Engineering Harness - a configuration repository that provides reusable agents, skills, and workflows for AI coding tools (OpenCode, Claude Code, Gemini CLI, and Pi). Configurations are symlinked to tool-specific directories via GNU Stow.
Setup Commands
# Install configurations (requires GNU Stow)
./setup.sh claude # Install Claude Code config to ~/.claude/
./setup.sh opencode # Install OpenCode config to ~/.config/opencode/
./setup.sh gemini # Install Gemini CLI config to ~/.gemini/
./setup.sh pi # Install Pi config to ~/.pi/agent/
./setup.sh all # Install all four
# Useful flags
./setup.sh <tool> --dry-run # Preview changes
./setup.sh <tool> --restow # Update existing symlinks
./setup.sh <tool> --delete # Remove symlinks
Architecture
Configuration Directories
claude/→ symlinks to~/.claude/(Claude Code)opencode/→ symlinks to~/.config/opencode/(OpenCode)gemini/→ symlinks to~/.gemini/(Gemini CLI)pi/→ symlinks to~/.pi/agent/(Pi)
All four contain parallel structures:
agents/- Specialized subagents (snake_case for OpenCode/Claude/Gemini, kebab-case for Pi)skills/orcommands/- Manual commands and auto-triggered behaviors
OpenCode additionally has commands/ (separate from skills), while Claude Code implements commands as skills with disable-model-invocation: true. Gemini CLI uses TOML format for both commands and skills. Pi uses prompts/ for command-equivalent prompt templates and includes an extensions/ directory with the subagent extension for multi-agent workflows.
Thoughts Directory (Context Engineering)
thoughts/
├── shared/ # Team-wide documents
│ ├── tickets/ # Work items (use ticket-template.md)
│ ├── plans/ # Implementation plans
│ └── research/ # Research documents
├── global/ # Cross-repository concerns
└── {username}/ # Personal notes
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.
- 6d ago First seen · 98 lines · 1,068 tokens per session scan A 54850c9e0034
ai-engineering-harness CLAUDE.md is an instructions file published in the GitHub repository adrielp/ai-engineering-harness (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,068 tokens to every session, about $0.0053 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.
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).
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.
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.
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.
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 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).