Borrowing it
Nothing to install: this file belongs to MontrealAI/AGI-Alpha-Agent-v0. 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/MontrealAI/AGI-Alpha-Agent-v0/main/AGENTS.mdgit clone --depth 1 https://github.com/MontrealAI/AGI-Alpha-Agent-v0Wrote 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/montrealai/agi-alpha-agent-v0/agents-md)<a href="https://agentmods.dev/instructions/montrealai/agi-alpha-agent-v0/agents-md"><img src="https://agentmods.dev/badge/instructions/montrealai/agi-alpha-agent-v0/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/montrealai/agi-alpha-agent-v0/agents-md"><img src="https://agentmods.dev/badge/instructions/montrealai/agi-alpha-agent-v0/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 | $0.06944 | $0.06944 |
| Opus 5.5 | $0.02778 | $0.02778 |
| Sonnet 5.5 | $0.01389 | $0.01389 |
| Haiku 4.5 | $0.00694 | $0.00694 |
Grade A, and why
AGI-Alpha-Agent-v0 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 15d 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 — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.
See docs/DISCLAIMER_SNIPPET.md
Contributor Guide
This repository contains the Alpha-Factory v1 package and demos. The instructions below apply to all contributors and automated agents.
Table of Contents
- Development Environment
- Coding Style
- Pull Requests
- Troubleshooting
- Code of Conduct
- Security Policy
- Wheel Signing
All contributors must follow the Code of Conduct. Please report security vulnerabilities as described in our Security Policy.
Prerequisites
- Python 3.11–3.13 (Python ≥3.11, <3.14)
- Docker and Docker Compose (Compose ≥2.20 for the current demo profiles)
- Git
- Node.js 22.17.1 for the web client and browser demo. A
.nvmrcis provided, so runnvm usebefore installing Node dependencies. - See Updating Browser Assets for instructions on refreshing the Pyodide runtime used by the Insight Browser demo.
- Keep
package-lock.jsonunder version control sonpm cireproduces the same dependency tree. - The project expects
pre-commit4.2.0. CI installs the same version withpip install pre-commit==4.2.0. - Run
python alpha_factory_v1/scripts/preflight.pyto validate these tools. - Run
FULL_INSTALL=1 ./codex/setup.shto install the locked development dependencies and set up the git hooks. The script attempts to installpre-commitautomatically. Ifpre-commitisn't found, runpip install pre-commit==4.2.0and re-run the script. - The first
pre-commit runmay take several minutes as it builds tool environments. - Install
pytestandprometheus_clientusingpython check_env.py --auto-installorpip install pytest prometheus_client. - Setting
ALPHA_FACTORY_FULL=1forcescheck_env.pyto install heavy extras even without--auto-install.
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.
- 15d ago Changed · +5 lines · +83 tokens per session a85aa6dbb131
- 16d ago Changed · +5 lines · +84 tokens per session 3bb975022325
- 1mo ago Changed · +1 lines · +28 tokens per session 9097df5e88ca
- 1mo ago Changed · +112 tokens per session 1b2ca9a3cbeb
- 1mo ago Changed · +4 lines · +71 tokens per session 0e75fd7630fd
- 2mo ago First seen · 472 lines · 6,566 tokens per session scan A 221f1c54f6c0
AGI-Alpha-Agent-v0 AGENTS.md is an instructions file published in the GitHub repository MontrealAI/AGI-Alpha-Agent-v0 (308 stars, last pushed 8d ago), licensed Apache-2.0. It adds 6,944 tokens to every session, about $0.0278 per session on Opus 5.5. 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.
AGI-Alpha-Agent-v0 AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| AGI-Alpha-Agent-v0 AGENTS.mdMontrealAI/AGI-Alpha-Agent-v0 | Instructions file | 308 | 8d ago | Apache-2.0 | A | 6,944 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |