Borrowing it
Nothing to install: this file belongs to WAHIB-EL-KHADIRI/AgentOS. 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/WAHIB-EL-KHADIRI/AgentOS/main/AGENTS.mdgit clone --depth 1 https://github.com/WAHIB-EL-KHADIRI/AgentOSWrote 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/wahib-el-khadiri/agentos/agents-md)<a href="https://agentmods.dev/instructions/wahib-el-khadiri/agentos/agents-md"><img src="https://agentmods.dev/badge/instructions/wahib-el-khadiri/agentos/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/wahib-el-khadiri/agentos/agents-md"><img src="https://agentmods.dev/badge/instructions/wahib-el-khadiri/agentos/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 | $0.00409 | $0.00409 |
| Opus 5.5 | $0.00164 | $0.00164 |
| Sonnet 5.5 | $0.00082 | $0.00082 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
AgentOS 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 2mo 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.
What it actually says
Development Guide
This document describes how AgentOS is structured and how to work with it effectively. It is written for developers — whether human or AI-assisted — who need to understand the project conventions.
Before Making Changes
- State the goal in one sentence when the scope is non-trivial.
- Identify the affected area: runtime, supervisor, CLI, dashboard, docs, tests, CI, SDKs, or demo assets.
- Choose the smallest safe change that handles the request.
- Name meaningful risks when runtime, lifecycle, security, or public APIs are involved.
Conventions
- Prefer small patches over broad rewrites.
- Follow existing project patterns before introducing new abstractions.
- Keep documentation honest and specific.
- Do not add generated artifacts, build output, dependency folders, or fake outputs.
- Do not change public APIs unless the task requires it. If a public API must change, document it clearly.
Runtime Guidelines
For runtime changes, prefer correctness over convenience:
- lifecycle events must be consistent
- spawn success must reflect the actual process state
- stop and timeout behavior must be explicit
- replay and demo claims must be reproducible
Demo Honesty
AgentOS demos must show real project behavior. Do not fabricate outputs, traces, logs, recovery behavior, or benchmark results. If something is experimental, planned, partial, or not production-ready, say so plainly.
Verification
Always run checks that match the change. For broad repository changes:
bash scripts/check.sh
If a required check cannot be run, report the reason honestly along with the remaining risk. Do not imply validation that did not happen.
Security
Do not add secrets, tokens, credentials, private keys, or personal state to the repository. Treat filesystem access, process spawning, networking, auth, logs, and replay data as security-sensitive areas.
Honesty over hype. Contributor trust is part of the product.
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.
- 2mo ago First seen · 59 lines · 409 tokens per session scan A afe35cdf2fa3
AgentOS AGENTS.md is an instructions file published in the GitHub repository WAHIB-EL-KHADIRI/AgentOS (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 409 tokens to every session, about $0.0016 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 2026-08-31.
AgentOS AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| AgentOS AGENTS.mdWAHIB-EL-KHADIRI/AgentOS | Instructions file | 7 | yesterday | Apache-2.0 | A | 409 | 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 | yesterday | 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 |