Borrowing it
Nothing to install: this file belongs to joe-broadhead/open-cowork. 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/joe-broadhead/open-cowork/master/AGENTS.mdgit clone --depth 1 https://github.com/joe-broadhead/open-coworkWrote 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/joe-broadhead/open-cowork/agents-md)<a href="https://agentmods.dev/instructions/joe-broadhead/open-cowork/agents-md"><img src="https://agentmods.dev/badge/instructions/joe-broadhead/open-cowork/agents-md.svg" alt="Measured on agentmods" 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 | $0.01466 | $0.01466 |
| Opus 5 | $0.00733 | $0.00733 |
| Sonnet 5 | $0.00293 | $0.00293 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
open-cowork 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Open Cowork is an Electron + TypeScript monorepo: desktop product layer on OpenCode (execution engine), plus Durable Gateway, Cloud, and Wiki. Package manager: [email protected]. Node: see .nvmrc (≥22.22.3). Default branch: master.
OpenCode owns execution (sessions, MCP, approvals, tools, streaming). Open Cowork owns composition (desktop UI, packaging, config, workflows, branding). Do not invent a second agent runtime.
Commands
pnpm install # install (frozen lockfile in CI)
pnpm dev # desktop dev
pnpm lint # eslint + design tokens + cycles + boundaries
pnpm lint:dead-code # canonical all-workspace Knip gate
pnpm typecheck # packages + desktop (slow; prefer scoped below)
pnpm test # monorepo unit/integration (excludes full gateway suite path in some flows)
pnpm test:gateway # Durable Gateway (cowork-gateway) vitest
pnpm test:renderer # packages/app renderer tests
pnpm test:e2e # desktop e2e (needs display)
pnpm docs:build # MkDocs strict
pnpm build # full monorepo build (ask first unless release)
git diff --check # no trailing whitespace
Scoped / fast loops
pnpm --filter @open-cowork/desktop typecheck
pnpm --filter cowork-gateway exec vitest run src/__tests__/some.test.ts
pnpm --filter @open-cowork/app exec vitest run path/to/file.test.ts
pnpm eslint --fix path/to/file.ts
pnpm exec tsc -p products/gateway/tsconfig.json --noEmit
Extra when relevant: pnpm audit:prod / pnpm audit:full (dependency security), pnpm perf:check, pnpm boundaries:check, pnpm --dir apps/desktop dist:ci.
Boundaries
Always
- Read files, list dirs, search the repo
- Run scoped lint / typecheck / unit tests for files you touch
- Preserve OpenCode-vs-composition ownership; change behavior in code/config, not prompt-only patches
- Prefer MCP tools over shell when a target system has an MCP
- Use design tokens /
@open-cowork/uifor UI (no raw palette hard-codes)
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.
- 8d ago First seen · 117 lines · 1,466 tokens per session scan A d7cdda2fdcf8
open-cowork AGENTS.md is an instructions file published in the GitHub repository joe-broadhead/open-cowork (11 stars, last pushed 3d ago), licensed MIT. It adds 1,466 tokens to every session, about $0.0073 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.
Other instructions, from other repositories
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.
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.
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 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).
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.