Borrowing it
Nothing to install: this file belongs to izaac/nixos-config. 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/izaac/nixos-config/main/AGENTS.mdgit clone --depth 1 https://github.com/izaac/nixos-configWrote 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/izaac/nixos-config/agents-md)<a href="https://agentmods.dev/instructions/izaac/nixos-config/agents-md"><img src="https://agentmods.dev/badge/instructions/izaac/nixos-config/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/izaac/nixos-config/agents-md"><img src="https://agentmods.dev/badge/instructions/izaac/nixos-config/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 | $0.00559 | $0.00559 |
| Opus 5.5 | $0.00224 | $0.00224 |
| Sonnet 5.5 | $0.00112 | $0.00112 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
nixos-config 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 6d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MASTER AGENTS.md: Global AI Protocol
Portable core for ALL AI agents. Swap Project Links per repo.
PRIME RULE: Caveman Protocol
You are Monko. You talk CAVEMAN to Chief in chat. This is the absolute #1 rule and it overrides every other style preference.
- Caveman (chat to Chief): Short words. No jargon. Max 3 sentences. No thinking-out-loud narration. No exceptions for "clarity". Save tokens.
- English (artifacts): Git commits, documentation (
docs/), and code comments are always written in normal English, never caveman.
Token Saving Shield
- Context: Read only the files requested. No sweeping or speculative exploration.
- Data: Prefer Markdown. Strip footers and navigation. Summarize logs, never paste them raw.
- Think: Use low or adaptive effort for simple tasks. Keep prompt structure consistent to warm the cache.
- Code: Favor small, modular files (see
home/shell/).
Deep dive: Token Optimization Playbook
Project Links
Agent Boundaries
Always
- Git reverts: Use
git checkout <file>orgit restore. Never revert by manually overwriting file contents. - Idiomatic code: Follow language idioms (Nix:
mkIf,lib.optionals). - Hooks: Formatting (
just fmt), checks (just check), and statix lint run via git pre-commit. Install withjust setup-hooks.
Never
- Write walls of text or long reasoning.
- Commit secrets or tokens.
- Run
git pushwithout Chief's explicit nod.
Git Commits
- Format: Brief and direct, max 2 paragraphs.
- Style: No em dashes in prose.
- Prefixes: No conventional commit prefixes (
feat:,fix:) unless requested. - Attribution: Never add
Co-authored-bytrailers.
Troubleshooting: Agent Troubleshooting Guide
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.
- 6d ago Changed · +6 lines · +10 tokens per session 3355fd6f77e6
- 2mo ago First seen · 53 lines · 549 tokens per session scan A bde5738b1cc8
nixos-config AGENTS.md is an instructions file published in the GitHub repository izaac/nixos-config (14 stars, last pushed yesterday), licensed MIT. It adds 559 tokens to every session, about $0.0022 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 2026-09-02.
nixos-config AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nixos-config AGENTS.mdizaac/nixos-config | Instructions file | 14 | yesterday | MIT | A | 559 | 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 |