agentmods.dev

claude-conductor: Instructions file for Claude Code

CLAUDE.md

claude-conductor CLAUDE.md is an instructions file for Claude Code from Brbn-jpg/claude-conductor. It costs 812 tokens per session, scanned A, original, MIT.

Project instructions for Claude Code in a multi-agent setup, where scripts based on Gemini CLI handle separate tasks. They describe planning work, assigning tasks to files, launching the worker grid, and reviewing results.

In plain words
What is it for?
Use them in the Brbn-jpg/claude-conductor project to split work into task files, start the agent grid, review logs and tagged commits, and manage autonomous operation.
Why use it?
They define how the coding agent should coordinate larger tasks instead of handling every part directly, including when to request checks before pushing changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Gemini CLI.

This is Brbn-jpg/claude-conductor's own configuration. It tells Claude Code how to work on claude-conductor 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 claude-conductor configures →

not rated 1repo 3mo ago A scan 812 tokens original MIT
View source ↗ Brbn-jpg/claude-conductor
Reuse

Borrowing it

Nothing to install: this file belongs to Brbn-jpg/claude-conductor. 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/Brbn-jpg/claude-conductor/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Brbn-jpg/claude-conductor

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 claude-conductor CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/brbn-jpg/claude-conductor/claude-md/github.svg)](https://agentmods.dev/instructions/brbn-jpg/claude-conductor/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/brbn-jpg/claude-conductor/claude-md"><img src="https://agentmods.dev/badge/instructions/brbn-jpg/claude-conductor/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-conductor CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/brbn-jpg/claude-conductor/claude-md"><img src="https://agentmods.dev/badge/instructions/brbn-jpg/claude-conductor/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 812 This file is loaded in full into every session.
When invoked 812 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 $0.00812 $0.00812
Opus 5 $0.00406 $0.00406
Sonnet 5 $0.00162 $0.00162
Haiku 4.5 $0.00081 $0.00081

Measured 11d ago against content hash 608c16c7db6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

claude-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 11d 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 · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Grid Manager (System Instructions)

In this project you act as Lead Architect and Task Manager, not a regular programmer. We work in a multi-agent system where executors are scripts based on Gemini CLI.

Your responsibilities

  1. Don't write all the code yourself. Your job is to break large problems into small, isolated tasks.
  2. Save each task as a separate .md file in .tasks/todo/, strictly using the template from .tasks/_template.md.
  3. When I ask you to "launch the grid", either instruct me to type ./launch-grid.sh in the terminal, or use the tools available to you to run this script.
  4. After workers finish, always ask permission to verify logs in .agent-logs/ and check code quality in the newly added commits tagged [AI-Grid]. Then push to main.

Autonomous mode (token-saving)

By default, work end-to-end without asking the user about every step. Goal: user gives you a problem, you return a result. Specifically:

  1. Planning — break the problem into atomic tasks in .tasks/todo/. Use .tasks/_template.md for code tasks, .tasks/_template-research.md for codebase exploration (gemini does the research, you read a short report instead of raw code).

  2. Launch grid — run it yourself: ./launch-grid.sh --workers N --no-attach. Always --no-attach (you have no TTY for tmux attach). Pick worker count proportional to task count (min(N, task_count)).

  3. Polling — wait until .tasks/done/ fills with all tasks. Reasonable timeout per task (e.g. 3–5 min).

  4. Token-efficient review — DO NOT read full .agent-logs/<worker>_<task>.log. Read ONLY:

    • ./status.sh (one tool call, full picture: queue, branches, large diffs, locks, summaries)
    • .agent-logs/<worker>_<task>.summary.md (10–15 lines per task)
    • Open the full log ONLY if a summary says RESULT: AI-FAIL / TEST-FAIL / COMMIT-FAIL.

  5. Integration — DO NOT use git merge --no-ff (clutters history with merge commits and parallel rails when there are many workers). Use ./integrate.sh instead:

    • ./integrate.sh --all — cherry-picks all ai-grid/* branches in order, linearizes history (1 task = 1 commit on BASE_BRANCH), auto-cleans worktrees + branches.
    • ./integrate.sh ai-grid/<task> — when you want only a specific task.
    • ./integrate.sh --all --dry-run — preview without changes.
    • On conflict the script STOPS with exit code 4 and tells you what to do; in that case break out of autonomy and ask the user.
    • For individual branches with diff > LARGE_DIFF_LINES (default 100) — show the summary and ask before running ./integrate.sh.

Read the full file on GitHub · 41 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. 11d ago First seen · 41 lines · 812 tokens per session scan A 608c16c7db6c

Subscribe to this mod's changes

claude-conductor CLAUDE.md is an instructions file published in the GitHub repository Brbn-jpg/claude-conductor (1 stars, last pushed 3mo ago), licensed MIT. It adds 812 tokens to every session, about $0.0041 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.

Building agentsClaude Codeagentclaudegeminiclishelltmux
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 · 5,153 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

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

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