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 skills add wochap/nix-config --skill skillgit clone --depth 1 https://github.com/wochap/nix-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/skills/wochap/nix-config/skill)<a href="https://agentmods.dev/skills/wochap/nix-config/skill"><img src="https://agentmods.dev/badge/skills/wochap/nix-config/skill/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/skills/wochap/nix-config/skill"><img src="https://agentmods.dev/badge/skills/wochap/nix-config/skill.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 | $0.00033 | $0.00286 |
| Opus 5.5 | $0.00013 | $0.00114 |
| Sonnet 5.5 | $0.00007 | $0.00057 |
| Haiku 4.5 | $0.00003 | $0.00029 |
Grade A, and why
cartridge 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 13d 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
cartridge
A cartridge is a short markdown file with rules for one language or tool.
The user gave cartridge names as arguments (text after the command, maybe as User: ...).
Available: bash, cpp, go, javascript, lua, nix, nixos-options, nodejs, nvim-lua, python, rust, typescript, zig
Follow these steps exactly:
- Take each word of the arguments that is in the Available list. Other words are the task.
- For each name, use the read tool on
cartridges/<name>.mdin this skill directory. Example:nixmeans readcartridges/nix.md. - Read ALL listed cartridges before you do anything else. Do not skip any.
- If a name is not in the Available list, or there are no names, show the Available list and stop.
- After reading, reply with one line:
Loaded: <names>. - If there is task text, do the task now. If not, wait for the user's task.
- For the rest of the session, cartridge rules win over your own habits.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- cartridges/bash.md 5.3 KB
- cartridges/cpp.md 6.5 KB
- cartridges/go.md 5.8 KB
- cartridges/javascript.md 7.3 KB
- cartridges/lua.md 5.3 KB
- cartridges/nix.md 6.3 KB
- cartridges/nixos-options.md 7.1 KB
- cartridges/nodejs.md 7.0 KB
- cartridges/nvim-lua.md 7.4 KB
- cartridges/python.md 6.7 KB
- cartridges/rust.md 5.8 KB
- cartridges/typescript.md 6.5 KB
- cartridges/zig.md 7.5 KB
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.
- 13d ago Changed · -11 lines · -1 tokens per session f2b31a8ddc7d
- 20d ago Changed · +2 lines 3ea62e4985f5
- 21d ago First seen · 33 lines · 34 tokens per session scan A 52fab9487ad7
cartridge is a skill published in the GitHub repository wochap/nix-config (143 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 286 once invoked, about $0.0001 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 2026-09-25.
Other skills, from other repositories
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics…
technical-writing
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
unslop
Cut AI tells from any writing. Must always apply.
how
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for…
quality-code
Standards for writing or modifying handwritten source code. Use when implementing code changes or reviewing handwritten code. Do not use for browsing, explanation, diagnosis without implementation, generated code, or vendored code.
teach
Explain a body of work plainly so a person actually understands it. Runs the how and why skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.