Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/aidotnet/opencowork/agents-mdgit clone --depth 1 https://github.com/AIDotNet/OpenCoworkWrote 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/aidotnet/opencowork/agents-md)<a href="https://agentmods.dev/instructions/aidotnet/opencowork/agents-md"><img src="https://agentmods.dev/badge/instructions/aidotnet/opencowork/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 | $0.04459 | $0.04459 |
| Opus 5 | $0.02230 | $0.02230 |
| Sonnet 5 | $0.00892 | $0.00892 |
| Haiku 4.5 | $0.00446 | $0.00446 |
Grade A, and why
OpenCowork 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 4d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
OpenCowork is an Electron desktop app plus a terminal CLI that share one .NET Native Worker. Keep process boundaries explicit: system access stays in Main, UI state stays in Renderer, the agent loop belongs in the Worker, shared types go through src/shared.
This file is the working contract for humans and coding agents. Read it before changing code. Prefer a small, well-placed change over a large, clever one.
Code Design
Design first. Do not start from a file that happens to be open. Decide ownership, data flow, and the existing seam, then write the smallest change that fits.
Before you write
Answer these in order. If any answer is fuzzy, stop and look at the surrounding module — do not invent a new shape.
- Which layer owns this? Renderer (presentation), Main (host/OS/desktop persistence), Worker (agent loop/tools/jobs),
src/shared(contracts). Put the code in that layer, not in the caller that first noticed the need. - Does a seam already exist? IPC handler, Worker module, runtime contract, Zustand store, CLI reducer action, DAO. Extend it. Do not add a parallel path because the existing one feels awkward.
- What is the source of truth? One owner writes; everyone else reads a projection, event, or query. Do not let two layers mutate the same fact.
- What is the smallest honest change? A focused edit that matches neighbors. Not a framework, helper layer, or “while we are here” rewrite.
Non-negotiable boundaries
| Concern | Owner | Do not |
|---|---|---|
| Provider loop, tool execution, approvals, cancellation, hosted sessions, durable jobs/events | Native Worker | Iterate a provider or execute a tool from Main, Renderer, or CLI |
| Window, process supervision, credentials, OS capabilities, desktop session/message SQLite | Main | Let Renderer or Worker become the desktop transcript writer |
| Message presentation, drafts, scroll, panels, session UX | Renderer / CLI UI | Push UI-only state into the runtime protocol |
| Cross-process types, runtime commands/queries/events | src/shared then generated protocol |
Ad-hoc channel strings, duplicated DTOs, hand-edited *.g.cs / cli/src/vendor/* |
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.
- 4d ago First seen · 266 lines · 4,459 tokens per session scan A a82ddc355c87
OpenCowork AGENTS.md is an instructions file published in the GitHub repository AIDotNet/OpenCowork (632 stars, last pushed 5d ago), licensed Apache-2.0. It adds 4,459 tokens to every session, about $0.0223 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
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.