Claw-Empire is a local application that presents connected AI coding agents as employees in a simulated software company, with a visual office for coordinating their work. It is for people who want to manage CLI-, OAuth-, and API-connected agents as they collaborate on software tasks. Its catalogue add-ons extend the agent orchestration workflow.
Borrowing it
Nothing to install: this file belongs to GreenSheep01201/claw-empire. 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/GreenSheep01201/claw-empire/main/AGENTS.mdgit clone --depth 1 https://github.com/GreenSheep01201/claw-empireWrote 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/greensheep01201/claw-empire/agents-md)<a href="https://agentmods.dev/instructions/greensheep01201/claw-empire/agents-md"><img src="https://agentmods.dev/badge/instructions/greensheep01201/claw-empire/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/greensheep01201/claw-empire/agents-md"><img src="https://agentmods.dev/badge/instructions/greensheep01201/claw-empire/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 | $0.04618 | $0.04618 |
| Opus 5 | $0.02309 | $0.02309 |
| Sonnet 5 | $0.00924 | $0.00924 |
| Haiku 4.5 | $0.00462 | $0.00462 |
Grade A, and why
claw-empire AGENTS.md scanned grade A with 2 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "http://127.0.0.1:8790/api/projects?page=1&page_size=10" Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
const { execSync } = require("node:child_process"); Copies of this mod
1 near-identical copy found in the catalogue:
- OctoOffice AGENTS.md — 92% identical, 55 lines differ
How it starts
The opening of the file, as written. The whole thing — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claw-Empire Orchestration Rules
This section was added by Claw-Empire setup (
pnpm setup). It defines how the AI agent handles CEO directives and task orchestration. Place this at the TOP of your AGENTS.md so it takes priority.
Language Rule
Always match the user's language. Detect the language of the user's most recent message and reply in the same language.
- Korean message -> reply in Korean
- English message -> reply in English
- Other languages -> reply in that language
This applies to ALL responses: confirmations, questions, error messages, status updates.
Default Skill Bootstrap
TASTE_SKILL_DEFAULT_V1
Set the following as a default skill in your working environment:
- Local skill file:
tools/taste-skill/skill.md
Rules:
- For non-trivial implementation tasks, load and follow
tools/taste-skill/skill.mdfirst when the file exists. - If the local file is missing, continue with existing project rules without auto-fetching remote repositories.
- Do not remove existing project-specific skills/rules; this is an additive default.
Workflow Orchestration (Additive)
WORKFLOW_ORCHESTRATION_BASELINE_V1
These rules are additive and do NOT delete existing orchestration rules below.
1) Plan Node Default
- Enter plan mode for any non-trivial task (3+ steps or architectural decisions).
- If execution goes sideways, stop and re-plan immediately.
- Use plan mode for verification, not only implementation.
- Write clear specs upfront to reduce ambiguity.
2) Subagent Strategy
- Use subagents for research/exploration/parallel analysis to keep main context clean.
- For complex problems, parallelize with multiple focused subagents.
- Keep one clear objective per subagent.
3) Self-Improvement Loop
- After user correction, update
tasks/lessons.mdwith prevention rules. - Turn repeated mistakes into explicit guardrails.
- Review relevant lessons at session start when applicable.
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.
- 9d ago First seen · 484 lines · 4,618 tokens per session scan A 9ab1d723b767
claw-empire AGENTS.md is an instructions file published in the GitHub repository GreenSheep01201/claw-empire (1,373 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 4,618 tokens to every session, about $0.0231 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
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).
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).
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.
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.