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/sopaco/cowork-forge/agents-mdgit clone --depth 1 https://github.com/sopaco/cowork-forgeWrote 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/sopaco/cowork-forge/agents-md)<a href="https://agentmods.dev/instructions/sopaco/cowork-forge/agents-md"><img src="https://agentmods.dev/badge/instructions/sopaco/cowork-forge/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 | $0.02947 | $0.02947 |
| Opus 5 | $0.01473 | $0.01473 |
| Sonnet 5 | $0.00589 | $0.00589 |
| Haiku 4.5 | $0.00295 | $0.00295 |
Grade C, and why
cowork-forge AGENTS.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Command sanitization**: Dangerous commands (`rm -rf`, `sudo`, etc.) are blocked. Do not circumvent the command whitelist. How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Cowork Forge
This file provides AI coding agents with the context needed to work effectively on this project.
Project Overview
Cowork Forge is an AI-native multi-agent software development platform. It orchestrates specialized AI agents (Product Manager, Architect, Project Manager, Engineer) through a 7-stage pipeline to transform ideas into production-ready software.
Workspace Structure
crates/
├── cowork-core/ # Domain logic, pipeline, tools, agents (MAIN crate)
│ └── src/
│ ├── pipeline/ # 7-stage orchestration & stage executor
│ ├── domain/ # Project, Iteration, Memory aggregates
│ ├── tools/ # 40+ ADK tools + MCP integration
│ ├── agents/ # Agent wrappers (iterative, PM, legacy analyzer)
│ ├── interaction/ # InteractiveBackend trait (CLI/GUI abstraction)
│ ├── acp/ # Agent Client Protocol for external agents
│ ├── config_definition/ # Data-driven config (agents, stages, flows)
│ ├── instructions/ # Agent prompt library
│ ├── skills/ # agentskills.io standard skill system
│ ├── integration/ # Hook manager for external integrations
│ └── persistence/ # JSON-based storage
├── cowork-cli/ # CLI adapter (clap + dialoguer)
└── cowork-gui/ # Tauri + React GUI
├── src-tauri/ # Rust backend (Tauri commands + events)
└── src/ # React frontend (TypeScript + Ant Design)
Dev Environment Setup
Prerequisites
- Rust (edition 2024, stable toolchain)
- Node.js (for GUI frontend build)
- LLM API Key (OpenAI-compatible endpoint)
Build
# Build entire workspace
cargo build
# Release build
cargo build --release
# Build GUI only (installs frontend deps automatically)
cd crates/cowork-gui && cargo tauri dev
Run
# CLI
cargo run --package cowork-cli -- <command>
# GUI (development mode)
cd crates/cowork-gui && cargo tauri dev
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 · 263 lines · 2,947 tokens per session scan C b9cfed1a49f0
cowork-forge AGENTS.md is an instructions file published in the GitHub repository sopaco/cowork-forge (91 stars, last pushed 10d ago), licensed MIT. It adds 2,947 tokens to every session, about $0.0147 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
tide CLAUDE.md
Instructions for team-attention/tide, covering tide — monorepo, before building, define the work, rules, quick commands and desktop (v2 electron).
plannotator AGENTS.md
AGENTS.md instructions for backnotprop/plannotator, covering plannotator, project structure, server runtimes, installation and environment variables.
solo AGENTS.md
AGENTS.md instructions for solo-agent/solo, covering project testing rules and project service lifecycle rules.
superset AGENTS.md
AGENTS.md instructions for superset-sh/superset, covering superset monorepo, project structure, exception: shadcn/ui components, database and releases.
untether GEMINI.md
Gemini CLI instructions for littlebearapps/untether, covering untether — gemini instructions, stack & conventions, architecture, key rules and testing.
agent-tools AGENTS.md
AGENTS.md instructions for kairyou/agent-tools, covering agent instructions, build and test, layout, settled decisions and docs.