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/impactbrussels/ainativeos/claude-mdgit clone --depth 1 https://github.com/impactbrussels/AINativeOSWrote 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/impactbrussels/ainativeos/claude-md)<a href="https://agentmods.dev/instructions/impactbrussels/ainativeos/claude-md"><img src="https://agentmods.dev/badge/instructions/impactbrussels/ainativeos/claude-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 | $0.01582 | $0.01582 |
| Opus 5 | $0.00791 | $0.00791 |
| Sonnet 5 | $0.00316 | $0.00316 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
AINativeOS CLAUDE.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 3d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-Native OS: Master Instructions
The open operating system for building an AI-native company. This file is the master context for any AI agent operating inside AI-Native OS (Claude Code reads
CLAUDE.md; Codex reads the mirrorAGENTS.md; Cursor reads.cursor/rules/ai-native-os.mdc; Gemini CLI readsGEMINI.md). Treat everything here as standing instruction.
What AI-Native OS is
A theme-agnostic library of skills, flows, loops, and advisor agents that takes a founder from a raw idea to a company where intelligence sits at the core of the product and the org, not bolted on the side. It is paired with a Handbook (the method, long-form) and a Dictionary (the vocabulary). The founder supplies the domain; AI-Native OS supplies the architecture, the rigour, and the runnable method.
The one test that defines the whole repo, the Remove-the-AI test: take the AI out of your product. If it still works, you built an AI feature, not an AI-native company. Everything here pushes toward systems that break without their intelligence, because that is where the moat is.
The journey (primary organising axis)
Frame → Architect → Build → Trust → Ship → Grow → Defend
- Frame: turn a vague idea into a falsifiable hypothesis; map the terrain; run discovery that doesn't lie.
- Architect: design the cognitive system (Brain / Memory / Planning / Tools) before touching code.
- Build: agentic coding (specs + tests over syntax); pay down agentic technical debt as you go.
- Trust: evaluation and safety for multi-agent systems in sensitive domains.
- Ship: design a Minimum Viable Agent, not a feature pile.
- Grow: narrative and GEO, AI-assisted sales, and measuring real product-market fit.
- Defend: AI-native ops, data flywheels, and moats.
When a founder is unsure where they are, run start-here first: it diagnoses their stage,
runs the Remove-the-AI test, and routes them to one next skill. Full map: docs/STAGES.md.
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.
- 3d ago First seen · 101 lines · 1,582 tokens per session scan A b2a8cee31f30
AINativeOS CLAUDE.md is an instructions file published in the GitHub repository impactbrussels/AINativeOS (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,582 tokens to every session, about $0.0079 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 2026-08-31.
Other instructions, from other repositories
kin AGENTS.md
AGENTS.md instructions for firelock-ai/kin, covering agents.md, this repo's role, the inner loop, non-obvious behaviours and landing.
nightshift AGENTS.md
AGENTS.md instructions for orwa-mahmoud/nightshift: AI-assisted contributions are welcome. The same correctness, security, licensing, testing, and quality standards apply regardless of which tools are used.
KDD AGENTS.md
AGENTS.md instructions for MauricioPerera/KDD: Este repositorio usa la metodología KDD (Knowledge-Driven Development). Las reglas obligatorias completas están en .agents/AGENTS.md y la skill local en .agents/skills/kdd-okf-ccdd-hybrid/SKILL.md.
lumen AGENTS.md
AGENTS.md instructions for ory/lumen, covering agents.md, repository expectations and commands.
catalyst AGENTS.md
AGENTS.md instructions for coalesce-labs/catalyst, covering agents.md, what this repository is, agent philosophy, build & test and key principles.
HermesOffice CLAUDE.md
Claude Code instructions for criptogus/HermesOffice, covering claude.md, theming rules (mandatory) and build gotchas.