companion: Instructions file for Claude Code

CLAUDE.md

companion CLAUDE.md is an instructions file for Claude Code from The-Vibe-Company/companion. It costs 751 tokens per session, scanned A, original, MIT.

A set of repository instructions for Claude Code covering the project’s direction, initial checks, testing expectations, and Claude-specific notes. The repository is a Go control system for managing groups of long-running AI agents and their tools.

In plain words
What is it for?
Use it to guide Claude Code while working on the command-line tool, workspace configuration, agent deployment, secure environments, providers, memory storage, and related project components.
Why use it?
It gives the coding agent the project context and working rules it needs before making changes. It also points to the main instruction file when the two files differ.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is The-Vibe-Company/companion's own configuration. It tells Claude Code how to work on companion 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 companion configures →

About the project

Companion is a self-hosted, multi-tenant hub for managing personal and organizational SKILL.md libraries used by coding agents. It is for organizations that need to store, validate, version, share, install, update, and synchronize agent skills, with optional named companions that have persistent workspaces and chats. The catalogue skills, agents, and instructions are resources managed or used within this workflow.

The-Vibe-Company/companion · 2,401 stars · on GitHub · thecompanion.sh

Reuse

Borrowing it

Nothing to install: this file belongs to The-Vibe-Company/companion. 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-Vibe-Company/companion/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/The-Vibe-Company/companion

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 companion CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/the-vibe-company/companion/claude-md"><img src="https://agentmods.dev/badge/instructions/the-vibe-company/companion/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 751 This file is loaded in full into every session.
When invoked 751 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 $0.00751 $0.00751
Opus 5 $0.00376 $0.00376
Sonnet 5 $0.00150 $0.00150
Haiku 4.5 $0.00075 $0.00075

Measured 3d ago against content hash 2523a7549994, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

companion 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 · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contributor guidance

Companion is a self-hostable, multi-tenant Skills Hub. Read docs/vision.md, docs/product.md, docs/design.md, docs/PRD.md, and docs/testing.md before non-trivial changes. Frontend work follows root DESIGN.md.

Product and architecture

  • Organization → User; organization roles are Owner, Admin, Developer.
  • Skills use personal or org scope. Personal skills are creator-only with no admin override. Every member can manage organization skills. Share is the sole owner-only personal → org transition.
  • Organization and personal label trees organize skills without changing access.
  • External coding agents are delegated Skills Hub clients. Companion never launches them.
  • Hosted Companions, Box/Pi, chat, routines, triggers, plugin accounts, and native chat clients are retired.
  • Complete authorized workflows end to end. Do not ask users to configure integrations manually when Companion can do that with credentials it already holds.
  • TypeScript, pnpm workspaces, Turborepo, Drizzle, tRPC/REST, Better Auth, S3-compatible storage.
  • packages/db/src/schema.ts is the data source of truth. Scope every tenant row/query by org_id. RLS is defense in depth. packages/core has no Next.js dependency; contracts live in packages/contracts.
  • Secrets are envelope-encrypted, write-only, referenced by id, and never logged as plaintext.
  • Never execute skill package scripts on the control plane. Archives and transfer tickets fail closed.
  • Public releases pin exact immutable versions and checksums. GitHub sync and database cleanup are idempotent.
  • Keep architecture, product docs, and the bundled Companion skill aligned with behavior.

Development and completion

Use .conductor/settings.toml. Setup installs PostgreSQL 17 and lsof, plus optional local MinIO and Mailpit, then runs corepack enable && pnpm install. Run starts per-workspace PostgreSQL, optional storage/mail, API, worker, and web. Ports derive from CONDUCTOR_PORT: web +0, API +1, PostgreSQL +2, MinIO +3/+4, SMTP +5, Mailpit +6. Internal services bind loopback.

Read the full file on GitHub · 48 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 Changed · -160 lines · -2,508 tokens per session 2523a7549994
  2. 6d ago Changed · -6 tokens per session ecf8bdfbdce8
  3. 9d ago Changed · +149 lines · +2,315 tokens per session 32645e8a1329
  4. 11d ago First seen · 59 lines · 950 tokens per session scan A c022a598c15d

Subscribe to this mod's changes

companion CLAUDE.md is an instructions file published in the GitHub repository The-Vibe-Company/companion (2,401 stars, last pushed 3d ago), licensed MIT. It adds 751 tokens to every session, about $0.0038 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 2026-08-30.

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