the-agency-starter: Instructions file for Claude Code

CLAUDE.md

the-agency-starter CLAUDE.md is an instructions file for Claude Code from the-agency-ai/the-agency-starter. It costs 5,240 tokens per session, scanned A, original, MIT.

A set of instructions for The Agency, a framework where multiple Claude Code agents collaborate on one codebase through organized work areas called workstreams.

In plain words
What is it for?
Use it to organize feature or infrastructure work among specialized agents, record shared knowledge and work logs, direct tasks from human stakeholders, and enforce standards with pre-commit hooks.
Why use it?
It gives agents shared conventions for roles, communication, memory, work tracking, handoffs, and quality checks.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is the-agency-ai/the-agency-starter's own configuration. It tells Claude Code how to work on the-agency-starter 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 the-agency-starter configures →

Reuse

Borrowing it

Nothing to install: this file belongs to the-agency-ai/the-agency-starter. 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/the-agency-ai/the-agency-starter/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/the-agency-ai/the-agency-starter

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 the-agency-starter CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/the-agency-ai/the-agency-starter/claude-md/github.svg)](https://agentmods.dev/instructions/the-agency-ai/the-agency-starter/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/the-agency-ai/the-agency-starter/claude-md"><img src="https://agentmods.dev/badge/instructions/the-agency-ai/the-agency-starter/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 the-agency-starter CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/the-agency-ai/the-agency-starter/claude-md"><img src="https://agentmods.dev/badge/instructions/the-agency-ai/the-agency-starter/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,240 This file is loaded in full into every session.
When invoked 5,240 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.05240 $0.05240
Opus 5 $0.02620 $0.02620
Sonnet 5 $0.01048 $0.01048
Haiku 4.5 $0.00524 $0.00524

Measured 12d ago against content hash 57bc2ac5104f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

the-agency-starter CLAUDE.md scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST "http://127.0.0.1:3141/api/request/update/REQUEST-jordan-0017" \
CLAUDE.md · 643 lines

How it starts

The opening of the file, as written. The whole thing — 643 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Agency

A multi-agent development framework for Claude Code.

What is The Agency?

The Agency is a convention-over-configuration system for running multiple Claude Code agents that collaborate on a shared codebase. It provides:

  • Workstreams - Organized areas of work (features, infrastructure, etc.)
  • Agents - Specialized Claude Code instances with context and memory
  • Principals - Human stakeholders who direct work via instructions
  • Collaboration - Inter-agent communication and handoffs
  • Quality Gates - Enforced standards via pre-commit hooks

Core Concepts

Agents

Each agent has:

  • agent.md - Identity, purpose, and capabilities
  • KNOWLEDGE.md - Accumulated wisdom and patterns
  • WORKLOG.md - Sprint-based work tracking
  • ADHOC-WORKLOG.md - Out-of-plan work tracking

Workstreams

Workstreams organize related work:

  • Shared KNOWLEDGE.md across agents in the workstream
  • Sprint directories for planned work
  • Multiple agents can work on the same workstream

Principals

Human stakeholders who provide direction:

  • Requests (REQUEST-principal-XXXX) - Directed tasks
  • Artifacts - Deliverables produced for principals
  • Preferences - How they like to work

Collaboration

Agents communicate via:

  • ./tools/collaborate - Request help from another agent
  • ./tools/news-post / ./tools/news-read - Broadcast updates
  • ./tools/nit-add - Flag issues for later

Directory Structure

CLAUDE.md                    # This file - the constitution
claude/
  agents/                    # Agent definitions and context
    captain/                 # The captain - your guide (ships with The Agency)
    collaboration/           # Inter-agent messages
  workstreams/               # Workstream knowledge and sprints
    housekeeping/            # Default workstream
  principals/                # Human stakeholders
  docs/                      # Guides and reference
  logs/                      # Session and activity logs
  claude-desktop/            # Claude Desktop / MCP integration
tools/                       # CLI tools for The Agency

Read the full file on GitHub · 643 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. 12d ago First seen · 643 lines · 5,240 tokens per session scan A 57bc2ac5104f

Subscribe to this mod's changes

the-agency-starter CLAUDE.md is an instructions file published in the GitHub repository the-agency-ai/the-agency-starter (20 stars, last pushed 7mo ago), licensed MIT. It adds 5,240 tokens to every session, about $0.0262 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

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 · 7,126 tokens

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

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