the-agency: Instructions file for Claude Code

CLAUDE.md

the-agency CLAUDE.md is an instructions file for Claude Code from takoyaro/the-agency. It costs 713 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for maintaining a fictional-character-based plugin marketplace and its agents.

In plain words
What is it for?
Use it when adding, renaming, or removing an agent, updating the marketplace, or checking that the marketplace can be installed correctly.
Why use it?
It reduces mistakes when adding or changing an agent by keeping plugin files, marketplace entries, documentation, versions, and validation in sync.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions subagents; mentions Claude Code.

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

Reuse

Borrowing it

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

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 CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/takoyaro/the-agency/claude-md"><img src="https://agentmods.dev/badge/instructions/takoyaro/the-agency/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 713 This file is loaded in full into every session.
When invoked 713 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 $0.00713 $0.00713
Opus 5 $0.00357 $0.00357
Sonnet 5 $0.00143 $0.00143
Haiku 4.5 $0.00071 $0.00071

Measured 10d ago against content hash 8374a1092da3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

the-agency 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 10d 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 · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Agency — working notes

A Claude Code plugin marketplace of subagents, each cast as a fictional character whose competence fits the role. See README.md for the pitch and CONTRIBUTING.md for the full contribution bar.

Adding a cast member — checklist

When you add (or rename/remove) an agent, ALL of these must stay in sync — miss one and installs break or the docs lie:

  1. Agent fileplugins/<slug>/agents/<slug>.md. Slug is lowercase-hyphenated and is the character's name, e.g. mike-ehrmantraut. Copy _agent-template.md.
  2. .claude-plugin/marketplace.json — two entries: a standalone plugin for the agent, and the agent's path in the full-roster bundle's agents array.
  3. README.md roster table — add a row. The table has an Install slug column and it is load-bearing: the display name and the slug often differ (L → l-lawliet, Q → q, Gus Fring → gus-fring). People copy the slug to run /plugin install <slug>@the-agency; a missing or wrong slug is a real, silent pain. Never add a roster row without its exact slug.
  4. Validateclaude plugin validate . must pass before committing.

Bump the relevant version fields in marketplace.json when changing a released agent so installs pick up the change.

Shipping a skill

Some agents ship a skill (plugins/<char>/skills/<name>/SKILL.md + optional references/). Keep these in sync or it won't load:

  • Declare it on the bundle. Add the skill dir to the full-roster the-agency entry's skills array in marketplace.json (e.g. "skills": ["./plugins/red/skills/"]). The standalone plugin auto-scans its own skills/; the bundle does not — miss this and the skill silently fails to load for bundle installs.
  • Body flavorless and deferring to the agent's voice; bulky reference in references/ (progressive disclosure).
  • Bump versions, claude plugin validate .. Reference implementation: red:writing.

Rules that don't bend

  • Fictional characters only. No real people, living or dead — and no lightly-renamed biopic stand-ins. See CONTRIBUTING.md for why.
  • Competence first, character second. The disposition must genuinely fit the work. A great character who'd be useless at the job is a bad hire.
  • Voice is a wrapper, never a cost to correctness. Underneath every agent is a prompt that would do the job even with all the flavor stripped out.

Read the full file on GitHub · 36 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. 10d ago First seen · 36 lines · 713 tokens per session scan A 8374a1092da3

Subscribe to this mod's changes

the-agency CLAUDE.md is an instructions file published in the GitHub repository takoyaro/the-agency (1 stars, last pushed 2mo ago), licensed MIT. It adds 713 tokens to every session, about $0.0036 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

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

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

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