What is multiagent CLAUDE.md?

A set of instructions for a tool that uses six AI agents to take software tasks from a backlog through implementation, review, testing, and a commit.

It helps automate prioritized coding tasks, coordinate specialist agents, enforce protected paths, resume interrupted work, and create feature branches.

It gives the agents a shared process for dividing work, checking quality, and saving progress for human review.

How mopkobka57/multiagent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mopkobka57/multiagent. 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/mopkobka57/multiagent/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mopkobka57/multiagent

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mopkobka57/multiagent/claude-md/github.svg)](https://agentmods.dev/instructions/mopkobka57/multiagent/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/mopkobka57/multiagent/claude-md"><img src="https://agentmods.dev/badge/instructions/mopkobka57/multiagent/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mopkobka57/multiagent/claude-md"><img src="https://agentmods.dev/badge/instructions/mopkobka57/multiagent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,492 This file is loaded in full into every session.

When invoked 1,492 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.

Model	Per session	Once invoked
Fable 5.1	$0.01492	$0.01492
Opus 5.5	$0.00597	$0.00597
Sonnet 5.5	$0.00298	$0.00298
Haiku 4.5	$0.00149	$0.00149

Measured 2mo ago against content hash 5158be53dad7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

multiagent 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 2mo 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 · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multiagent — Instructions for Claude

What is this

Autonomous task execution system powered by Claude. Reads a backlog, picks tasks by priority, coordinates 6 AI agents (Orchestrator → Product → Analyst → Implementor → Reviewer → Visual Tester), runs quality gates, and commits to feature branches for human review.

Designed to be installed into any project via python -m multiagent init.

Language

Code, comments, commits — English.

Architecture

multiagent/
  __main__.py          CLI entry point (init, spec, --next, --task, --list, --batch)
  config.py            All settings (populated from multiagent.toml at import)
  project_config.py    TOML loader, auto-detection fallback
  core/                Engine
    pipeline.py        Standard task pipeline (branch → enrich → implement → review → commit)
    orchestrator.py    High-level commands (run_next, run_batch, etc.)
    agents.py          Agent definitions and Claude API calls
    prompt_builder.py  Prompt construction, spec discovery
    task_loader.py     Backlog parser (Markdown tables → Task objects)
    state.py           State persistence for resume support
    guardrails.py      Protected path enforcement
    quality_gates.py   Build/lint gates, screenshots
    git.py             Git operations (branch, commit, checkout)
    retry.py           Rate limit handling with exponential backoff
    spec_manager.py    Spec CRUD, versioning
    spec_creator.py    AI-powered spec generation from descriptions
    init.py            Project initialization logic
  analyzer/            Project detection + AI analysis (used by init)
  prompts/             Agent system prompts (Markdown templates)
  templates/           Scaffold templates for init (toml, backlog, contexts)
  server/              FastAPI web dashboard + process manager
  docs/                Full documentation (11 files)

Key concepts

Specs — Markdown files describing tasks. Statuses: stub → partial → full. Agents enrich stubs before implementation. See docs/backlog-format.md.
Foundational specs — files prefixed with _ in specs/, loaded into every agent's context (conventions, architecture).
Quality gates — shell commands (tsc, build) run after each implementation step. Configured in multiagent.toml.
Autonomy modes — supervised (confirm each step), batch (confirm per-task), autonomous (hands-off). See docs/autonomy-modes.md.
Web dashboard — FastAPI + Alpine.js SPA for managing tasks, specs, groups, and runs. Real-time logs via WebSocket. See docs/dashboard.md.
Spec groups — bundle related tasks to run sequentially on a shared branch. Created via dashboard UI.
Task types — feature (full pipeline), tech-debt/refactor/bugfix (skip Product agent), audit (read-only analysis).

Read the full file on GitHub · 122 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.

2mo ago First seen · 122 lines · 1,492 tokens per session scan A 5158be53dad7

Subscribe to this mod's changes

multiagent CLAUDE.md is an instructions file published in the GitHub repository mopkobka57/multiagent (5 stars, last pushed 7mo ago), licensed MIT. It adds 1,492 tokens to every session, about $0.0060 per session on Opus 5.5. 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.

multiagent CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
multiagent CLAUDE.mdmopkobka57/multiagent	Instructions file	5	7mo ago	MIT	A	1,492	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

multiagent: Instructions file for Claude Code