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/openclaw/nix-openclaw-tools/agents-mdgit clone --depth 1 https://github.com/openclaw/nix-openclaw-toolsWrote 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/openclaw/nix-openclaw-tools/agents-md)<a href="https://agentmods.dev/instructions/openclaw/nix-openclaw-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/openclaw/nix-openclaw-tools/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 | $0.00477 | $0.00477 |
| Opus 5 | $0.00238 | $0.00238 |
| Sonnet 5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
nix-openclaw-tools 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — nix-openclaw-tools
This repo packages OpenClaw-adjacent CLI tools and plugin metadata. It is part of the public OpenClaw Nix packaging boundary, not Josh's private machine config.
Boundary Model
- OpenClaw owns product/runtime behavior.
- nix-openclaw owns the batteries-included Nix module surface, runtime injection, launchd/systemd wiring, and package-contract checks.
- nix-openclaw-tools owns reproducible packages for tool CLIs and the plugin metadata/skills that describe them.
- nixos-config and other downstream machine repos should only choose hosts, secrets, accounts, and which plugins are enabled. If a downstream repo has to build a tool, copy a tool package, or hand-wire a tool into an agent PATH, fix this repo or nix-openclaw instead.
Packaging Rules
- Packages must be Garnix-cacheable for supported systems. Do not rely on Homebrew, globally installed Node/Python, Xcode state outside Nix, or runtime
npm/npx/uvx. - Prefer upstream release assets when they exist. Build from source only when release assets do not exist or are not suitable.
- If a tool is a first-party OpenClaw battery, add/update package, plugin metadata, checks, and auto-update logic together.
- QMD belongs here when packaged for Nix OpenClaw. The package should provide the
qmdCLI; nix-openclaw decides how to inject it into the OpenClaw runtime. - Do not expose tools globally by policy from this repo. Export packages and plugin metadata; let nix-openclaw place them on the correct agent/runtime PATH.
Automation
cmd/update-toolsis the release-asset updater. Keep it resilient: one upstream tool changing asset names should not silently rot the whole repo.- QMD freshness should be checked by automation too. Josh should not have to remember a separate QMD bump path.
cmd/sync-skillstracks OpenClaw skills from upstream main.- Garnix should build package checks for every supported package/system after update commits.
Workflow
- Trunk-based development on
main. - Keep commits small and logical.
- Run targeted package checks before committing; use CI/Garnix for expensive cross-platform proof.
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 · 32 lines · 477 tokens per session scan A 8682a091ed8c
nix-openclaw-tools AGENTS.md is an instructions file published in the GitHub repository openclaw/nix-openclaw-tools (53 stars, last pushed today), licensed MIT. It adds 477 tokens to every session, about $0.0024 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.