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/sapienxai/agentos/agents-mdgit clone --depth 1 https://github.com/SapienXai/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/sapienxai/agentos/agents-md)<a href="https://agentmods.dev/instructions/sapienxai/agentos/agents-md"><img src="https://agentmods.dev/badge/instructions/sapienxai/agentos/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 | $0.01175 | $0.01175 |
| Opus 5 | $0.00588 | $0.00588 |
| Sonnet 5 | $0.00235 | $0.00235 |
| Haiku 4.5 | $0.00118 | $0.00118 |
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 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.
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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Identity
AgentOS is the human operating layer above OpenClaw.
OpenClaw is the backend, runtime, orchestration, agent, tool, model, session, and gateway layer. AgentOS must not clone or replace OpenClaw. AgentOS should provide the operator-facing workspace, control, visibility, policy, and coordination layer on top of OpenClaw.
When in doubt:
- Use OpenClaw as the source of truth.
- Keep AgentOS as the control/UI/application layer.
- Do not duplicate OpenClaw backend functionality inside AgentOS.
Required Project Skill
Before making AgentOS code, UX, OpenClaw integration, security, release, or publishing changes, read:
docs/agentos-codex-skill.md
Keep all changes aligned with that skill.
If the task touches OpenClaw, releases, npm publishing, GitHub releases, auth, accounts, model credentials, API routes, local operator access, browser profiles, or security-sensitive behavior, the skill file is mandatory context, not optional background.
Project Language
- The project’s default language is English.
- Do not add Turkish content to the project unless the user explicitly asks for it.
- Keep user-facing copy in English, including UI text, placeholders, examples, documentation, seeded content, errors, empty states, release notes, and CLI output.
- Internal comments should also be English unless there is a strong reason otherwise.
Git
- All git commit messages must be written in English.
- Use concise, imperative commit subjects.
- Prefer Conventional Commits format, for example:
feat(auth): add session refresh. - Keep the subject line short, ideally under 72 characters.
- Default to a single-line commit message.
- Only add a commit body when extra context is genuinely necessary.
- If a body is needed, keep it brief and focused on why the change was made.
- Do not generate long commit messages or file-by-file summaries by default.
- Do not write commit messages in Turkish unless the user explicitly asks for it.
OpenClaw Integration Rules
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 · 112 lines · 1,175 tokens per session scan A d483fd4a5d82
AgentOS AGENTS.md is an instructions file published in the GitHub repository SapienXai/AgentOS (93 stars, last pushed 21d ago), licensed MIT. It adds 1,175 tokens to every session, about $0.0059 per session on Opus 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.
Other instructions, from other repositories
oryxos CLAUDE.md
Claude Code instructions for oryx-labs/oryxos, covering oryxos — claude code 项目指南, 技术栈, 模块结构（14 个）, 不可违背的原则（constitution） and 原则一：自实现 react loop.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.