code-conductor CLAUDE.md

A project-instruction file for Code Conductor, an AI agent coordination system. It explains the repository, documentation, development commands, and how coding agents should work with GitHub tasks and Git worktrees.

In plain words
What is it for?
Use it to guide agents through repository setup, documentation lookup, task handling, and development or testing work in Code Conductor projects.
Why use it?
It gives agents shared project context and working rules, reducing confusion when several agents contribute to the same codebase.

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/ryanmac/code-conductor/claude-md
Clone the repo
git clone --depth 1 https://github.com/ryanmac/code-conductor
Per session 2,962 This file is loaded in full into every session.
When invoked 2,962 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 $0.02962 $0.02962
Opus 5 $0.01481 $0.01481
Sonnet 5 $0.00592 $0.00592
Haiku 4.5 $0.00296 $0.00296

Measured yesterday against content hash 65f9074758bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-conductor 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 · 386 lines

How it starts

The opening of the file, as written. The whole thing — 386 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

Code Conductor is an AI agent coordination system designed to orchestrate multiple AI coding agents (like Claude Code, Conductor, Warp) working on the same codebase. It provides GitHub-native task management with automatic conflict prevention through git worktrees.

IMPORTANT: This is a template repository. When you encounter Code Conductor files in a project, they have been imported to enable automated agent coordination. Work autonomously based on GitHub Issues with the conductor:task label and the guidance in these files.

Documentation Map

CRITICAL: When starting work on any task, check if .conductor/documentation-map.yaml exists. This file contains:

  • Comprehensive project analysis and structure
  • Technology stack details and dependencies
  • List of completed vs. pending features
  • Implementation status and critical paths
  • Architectural decisions and constraints

If this file exists, load it to understand the project context before beginning work. This map is created by the [INIT] discovery task and provides essential context for all subsequent tasks.

Key Development Commands

Running Tests

# Run all tests
python -m pytest tests/ -v

# Run specific test file
python tests/test_basic.py
python tests/test_stack_detection.py

Linting and Formatting

# Check code formatting (without making changes)
black --check .conductor/scripts/ setup.py

# Apply formatting
black .conductor/scripts/ setup.py

# Run linting
flake8 .conductor/scripts/ setup.py --max-line-length=88 --extend-ignore=E203,W503

Validation Commands

# Validate conductor configuration
python .conductor/scripts/validate-config.py

# Check system dependencies
python .conductor/scripts/dependency-check.py

# Run health check
python .conductor/scripts/health-check.py

Architecture Overview

Core Components

Read the full file on GitHub · 386 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 First seen · 386 lines · 2,962 tokens per session scan A 65f9074758bc

Subscribe to this mod's changes

code-conductor CLAUDE.md is an instructions file published in the GitHub repository ryanmac/code-conductor (110 stars, last pushed 5mo ago), licensed MIT. It adds 2,962 tokens to every session, about $0.0148 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.