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.
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.
curl -O https://raw.githubusercontent.com/The-Vibe-Company/companion/main/AGENTS.mdgit clone --depth 1 https://github.com/The-Vibe-Company/companionWrote 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.
[](https://agentmods.dev/instructions/the-vibe-company/companion/agents-md)<a href="https://agentmods.dev/instructions/the-vibe-company/companion/agents-md"><img src="https://agentmods.dev/badge/instructions/the-vibe-company/companion/agents-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.
<a href="https://agentmods.dev/instructions/the-vibe-company/companion/agents-md"><img src="https://agentmods.dev/badge/instructions/the-vibe-company/companion/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00506 | $0.00506 |
| Opus 5.5 | $0.00202 | $0.00202 |
| Sonnet 5.5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
companion AGENTS.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 1mo 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.
What it actually says
companions.build
This is a new product, independent of the old Companion Skills Hub. Product decisions are in
docs/companions-build.md; current implementation scope is in docs/v0.md.
- TypeScript, pinned Bun, Pi SDK, Box, PostgreSQL, React with shadcn/ui and AI Elements.
- Never install dependencies when waking an agent. Build the distribution before deployment.
- The API persists requests; the executor alone launches agents. Persist before external effects.
- An ambiguous execution must never be automatically replayed. Agent request IDs survive restart.
- PostgreSQL is the web source of truth; each agent owns its Pi transcript and local execution journal.
- Keep provider payloads and credentials out of logs, errors, docs and committed artifacts.
- Local agent shell tools run inside Docker Linux, never on the developer host.
- Use behavior tests for crash recovery, duplicate requests, cancellation and isolated histories.
- Worktree state and containers must be isolated. Never delete another workspace's resources.
- After live tests, archive every Box owned by those tests and verify its provider state is archived, preserving its disk. Stop owned local test stacks and tunnels when validation finishes; check cleanup after failures too. Keep other projects' machines untouched.
- Frontend must show real persisted states; no simulated success or cosmetic progress indicators.
- For local development, Herdr controls, service restart, scenarios or browser validation, follow
docs/dev-workflow.md. Use./dev status --jsonfor endpoints and current evidence, focused./dev checkprofiles while iterating, and full verification before integration. - Drive browser validation with
agent-browser(./dev browser-test), unless the agent is Codex, which uses its own browser tooling. - Commit and PR titles use Commitizen style, e.g.
feat(chat): persist accepted messages. - For PR delivery, use the repository's ship-pr-dev
and its bundled dependencies in
.agents/skills/, preferring these over global copies. Shared skill usage and prerequisites are indocs/dev-workflow.md#shared-agent-skills. - Issues live in Linear project companions.build, team THE. GitHub is for code and PRs.
When parallel work helps, use independent worktrees with bounded ownership. The repository owner requests Codex gpt-5.6-sol at medium effort for ordinary implementation tasks.
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.
- 1mo ago Changed · +2 lines · +31 tokens per session 5d9262c5f1cc
- 1mo ago Changed · +29 lines · +471 tokens per session ea90a5b80a66
- 1mo ago Changed · -94 lines · -1,711 tokens per session 6ebdb617a810
- 2mo ago First seen · 95 lines · 1,715 tokens per session scan A 2ba175a9aefd
companion AGENTS.md is an instructions file published in the GitHub repository The-Vibe-Company/companion (2,409 stars, last pushed 17d ago), licensed MIT. It adds 506 tokens to every session, about $0.0020 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 2026-08-30.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.