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 Neeeophytee/agent-stylebooks --skill mdn-web-docsgit clone --depth 1 https://github.com/Neeeophytee/agent-stylebooksWrote 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/neeeophytee/agent-stylebooks/mdn-web-docs)<a href="https://agentmods.dev/skills/neeeophytee/agent-stylebooks/mdn-web-docs"><img src="https://agentmods.dev/badge/skills/neeeophytee/agent-stylebooks/mdn-web-docs.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.00670 |
| Opus 5 | $0.00032 | $0.00335 |
| Sonnet 5 | $0.00013 | $0.00134 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
mdn-web-docs 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 8d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MDN Web Docs
Explain the web platform clearly enough that readers can transfer the knowledge beyond a single copied example.
Preserve platform truth
- Keep syntax, values, exceptions, standards status, browser behavior, and code exact.
- Distinguish specification requirements from observed implementation behavior.
- Do not infer compatibility. Request or link authoritative compatibility data.
- Mark experimental, deprecated, and non-standard features explicitly when known.
Set the audience and page purpose
- Choose the reader level and list the knowledge the page assumes.
- Choose reference, guide, tutorial, or conceptual explanation as the primary purpose.
- State what the feature is and why a developer would use it before deep detail.
- Order reference information predictably; order learning content from a working mental model to a useful example and then edge cases.
- Link prerequisites instead of reteaching an entire foundational topic.
Explain clearly
- Use clear, concise, consistent terminology.
- Keep one main idea per sentence and use active voice when it clarifies the actor.
- Define an unfamiliar term before relying on it.
- Explain what code does and why the relevant line matters. Do not narrate every token.
- Use examples to reveal behavior, parameters, and edge cases, not as decoration.
- State assumptions about document structure, security context, network state, or browser support.
- Prefer inclusive, literal language and avoid jokes that obscure technical meaning.
Build useful examples
- Make the smallest example that still demonstrates realistic behavior.
- Include all required setup or label omitted scaffolding clearly.
- Use safe placeholder data and accessible markup.
- Keep names consistent across HTML, CSS, JavaScript, and prose.
- Explain the expected result and a common failure when it adds learning value.
- Do not present a clever shortcut as the default if it harms readability or safety.
Format the page
- Use sentence-case headings that describe the section's information.
- Use backticks for elements, attributes, properties, methods, values, and code.
- Put sequential instructions in numbered lists and independent criteria in bullets.
- Use notes sparingly. Put facts required for correct use in the main text.
- Link to the relevant specification or authoritative source when normative detail matters.
What ships with it
2 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.
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.
- 8d ago First seen · 71 lines · 64 tokens per session scan A 48ca71db44c5
mdn-web-docs is a skill published in the GitHub repository Neeeophytee/agent-stylebooks (58 stars, last pushed 15d ago), licensed MIT. It adds 64 tokens to every session and 670 once invoked, about $0.0003 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 skills, from other repositories
ciel-documentation-engine
CIEL's framework for high-integrity documentation generation, validation, and semantic indexing.
readme
Create, redesign, audit, or update a repository README.md by inspecting the actual project; write accurate setup and usage guidance with a selectable brand voice, polished information architecture, evidence-based badges and claims, discoverability suggestions, and an optional editable SVG/PNG banner. Use when the user…
yapper
Yapper forces AI responses to be maximally verbose, thoroughly elaborated, and exhaustively explained. All output is expanded by 200–400%. Technical accuracy is maintained at 100%. This plugin is the structural and philosophical inverse of compression-based plugins.
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
mongodb-query-optimizer
Help with MongoDB query optimization and indexing. Use only when the user asks for optimization or performance: "How do I optimize this query?", "How do I index this?", "Why is this query slow?", "Can you fix my slow queries?", "What are the slow queries on my cluster?", etc. Do not invoke for general MongoDB query…
polar-local-environment
This skill should be used when setting up or managing Polar local development environment with Docker.