labor.fun CLAUDE.md

labor.fun CLAUDE.md is an instructions file for coding agents from BreadchainCoop/labor.fun. It costs 1,425 tokens per session, scanned A, original, MIT.

A framework for running AI assistants for multiple organisations and chat channels such as Telegram, Slack, and Discord. It runs each group’s Claude agent in its own container with separate files and memory.

In plain words
What is it for?
It helps maintain the Node.js service, configure organisation profiles, route channel messages to Claude agents, and manage rules, memory, files, and plugins.
Why use it?
It keeps different organisations and conversation groups isolated, so their identities, knowledge, files, and runtime data do not get mixed together.

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/breadchaincoop/labor.fun/claude-md
Clone the repo
git clone --depth 1 https://github.com/BreadchainCoop/labor.fun

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 labor.fun CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/breadchaincoop/labor.fun/claude-md.svg)](https://agentmods.dev/instructions/breadchaincoop/labor.fun/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/breadchaincoop/labor.fun/claude-md"><img src="https://agentmods.dev/badge/instructions/breadchaincoop/labor.fun/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,425 This file is loaded in full into every session.
When invoked 1,425 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 $0.01425 $0.01425
Opus 5 $0.00713 $0.00713
Sonnet 5 $0.00285 $0.00285
Haiku 4.5 $0.00143 $0.00143

Measured 3d ago against content hash 6a843351fa3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

labor.fun 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 3d 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 · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

labor.fun

A standalone, multi-org framework for multi-channel AI assistants. Runs Claude agents in isolated containers with per-group memory. (Internal container protocol keeps the nanoclaw codename.)

Quick Context

Single Node.js process. Channels (Telegram, Slack, Discord) self-register at startup. Messages route to Claude Agent SDK running in Docker containers. Each group has isolated filesystem and memory.

The framework is org-agnostic. Every org-specific thing — identity, KB, people, runtime state — lives in a profile under profiles/<name>/. The active profile is chosen at startup via LABOR_PROFILE (else the single profile present, else the repo root for legacy/dev). profile.config.json is the single source of truth for brand/identity/paths; the code reads it via src/profile.tssrc/config.ts. Never hardcode an org name, path, or GitHub org in src/ — derive it from the profile/config. See docs/NEW-ORG-GUIDE.md and docs/PLUGINS.md.

Rules & Operational Knowledge

Breadbrich Engels's behavior is defined by structured rule files in rules/. These are the authoritative source for:

Rule Set Path Governs
Access Control rules/access-control/ Who can see/do what, privacy enforcement
Knowledge Base rules/knowledge-base/ KB structure, document format, task management
Messaging rules/messaging/ Channel formatting, cross-platform send
Scheduling rules/scheduling/ Cron tasks, scripts, API credit conservation
Identity & RBAC rules/identity/ User resolution, tag hierarchy, platform mapping
Transcripts rules/transcripts/ Meeting transcript processing, action item extraction
Approvals rules/approvals/ Reusable human-in-the-loop approval primitive: gated action classes, who approves, expiry
GitHub Integration rules/integrations/ GitHub issues/PRs/code/Actions on the org's GitHub org (githubOrg in the active profile)
Linear Integration rules/integrations/ Linear issues/projects/comments in the org's Linear workspace (LINEAR_API_KEY)

Read the full file on GitHub · 99 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. 3d ago First seen · 99 lines · 1,425 tokens per session scan A 6a843351fa3f

Subscribe to this mod's changes

labor.fun CLAUDE.md is an instructions file published in the GitHub repository BreadchainCoop/labor.fun (2 stars, last pushed 6d ago), licensed MIT. It adds 1,425 tokens to every session, about $0.0071 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

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

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 · 5,182 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 · 4,345 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

next.js 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