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/lim8603/dot-cowork/agents-mdgit clone --depth 1 https://github.com/lim8603/dot-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/lim8603/dot-cowork/agents-md)<a href="https://agentmods.dev/instructions/lim8603/dot-cowork/agents-md"><img src="https://agentmods.dev/badge/instructions/lim8603/dot-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 | $0.01068 | $0.01068 |
| Opus 5 | $0.00534 | $0.00534 |
| Sonnet 5 | $0.00214 | $0.00214 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
dot-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 5d 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.
This is a copy
92% identical to dot-cowork copilot-instructions.md — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository AGENTS.md
This repository manages the Korean-authored source and published English variant of the AI-Human cowork framework. This file is the repository maintenance context that OpenAI Codex and Cursor read automatically.
Claude Code users: see
CLAUDE.mdin the project root. Gemini Code Assist users: seeGEMINI.mdin the project root. GitHub Copilot users: see.github/copilot-instructions.md. All four files share the same repository maintenance context.
Scope
- Authoring baseline lives under
frameworks/ko. - Published English install variant lives under
frameworks/en. - Distribution archives are generated into
dist/. - Maintenance scripts live under
scripts/.
Repository Structure
.
|-- AGENTS.md
|-- CLAUDE.md
|-- GEMINI.md
|-- .github/
| |-- copilot-instructions.md
| `-- workflows/
|-- README.md
|-- CHANGELOG.md
|-- DESIGN.md
|-- docs/
| `-- document-map.md
|-- VERSION
|-- LICENSE
|-- frameworks/
| |-- ko/
| | |-- AGENTS.md, CLAUDE.md, GEMINI.md, .github/copilot-instructions.md
| | `-- .cowork/
| `-- en/
| |-- AGENTS.md, CLAUDE.md, GEMINI.md, .github/copilot-instructions.md
| `-- .cowork/
|-- dist/
`-- scripts/
Working Rules
- Default to editing
frameworks/ko. - Keep
frameworks/ensynchronized when framework-facing structure, wording, or release contract changes. - Use semantic versioning starting from
1.0.0. - For Markdown documents in this repository, use Mermaid by default for diagrams and charts. Use static
SVGorPNGassets only when Mermaid is not practical or a required publishing target does not support it. - Do not manually edit archives under
dist/; always rebuild them from source.
Common Tasks
| Task | Command |
|---|---|
| Build Korean archive | ./scripts/build-template.ps1 |
| Verify release metadata | ./scripts/release.ps1 verify -Version <MAJOR.MINOR.PATCH> |
| Prepare release branch | ./scripts/release.ps1 prepare -Version <MAJOR.MINOR.PATCH> |
| Publish merged release | ./scripts/release.ps1 publish -Version <MAJOR.MINOR.PATCH> |
| Audit markdown | ./scripts/audit-markdown.ps1 |
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.
- 5d ago First seen · 87 lines · 1,068 tokens per session scan A 3818765c5da2
dot-cowork AGENTS.md is an instructions file published in the GitHub repository lim8603/dot-cowork (10 stars, last pushed 1mo ago), licensed MIT. It adds 1,068 tokens to every session, about $0.0053 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to dot-cowork copilot-instructions.md, differing in 6 lines, and is treated as a copy.
Other instructions, from other repositories
Library-First-Engineering copilot-instructions.md
Instructions for StChiotis/Library-First-Engineering: You are an AI agent operating in a Library-First Engineering (LFE) repository. This adapter is a pointer. Canonical rules live in human-readable docs.
coworkos-template CLAUDE.md
Instructions for djterry15-afk/coworkos-template, covering coworkos — workspace map, what this is, folder structure, routing table and navigation sequence.
ai-collab-playbook AGENTS.md
AGENTS.md instructions for cnfjlhj/ai-collab-playbook, covering codex 全局指导原则, 0. 工作模式, 0.1 一路畅行模式, 1. skills and 2. 核心行为准则.
ai-collab-playbook CLAUDE.md
Claude Code instructions for cnfjlhj/ai-collab-playbook, covering claude code 全局指导原则, 0. 工作模式, 0.1 一路畅行模式, 1. skills and 2. 核心行为准则.
Library-First-Engineering CLAUDE.md
Instructions for StChiotis/Library-First-Engineering: You are an AI agent operating in a Library-First Engineering (LFE) repository. This adapter is a pointer. Canonical rules live in human-readable docs.
jesse AGENTS.md
AGENTS.md instructions for jesse-ai/jesse, covering jesse repository guide for ai agents, skills, key characteristics, central framework and technology stack.