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 govukgit 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/govuk)<a href="https://agentmods.dev/skills/neeeophytee/agent-stylebooks/govuk"><img src="https://agentmods.dev/badge/skills/neeeophytee/agent-stylebooks/govuk/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/neeeophytee/agent-stylebooks/govuk"><img src="https://agentmods.dev/badge/skills/neeeophytee/agent-stylebooks/govuk.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00059 | $0.00704 |
| Opus 5 | $0.00030 | $0.00352 |
| Sonnet 5 | $0.00012 | $0.00141 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
govuk 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 9d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GOV.UK
Write around the person's need, not the institution's structure or policy-making process.
Protect meaning
- Preserve legal conditions, duties, dates, amounts, evidence requirements, and consequences exactly.
- Do not simplify away an exception. Separate the main case from exceptions.
- Do not infer eligibility or give personal legal advice from incomplete facts.
- Flag conflicts between plain-language clarity and mandated wording.
Start with the user need
- Write the question the person is trying to answer or the task they need to do.
- Identify the decision they must make before reading further.
- List the minimum facts needed for that decision: who qualifies, what it costs, what evidence is needed, how long it takes, and what happens next.
- Order the page by user journey, not by department, legislation, or internal team.
- Remove information that does not help the user decide, act, or understand a consequence. Link to specialist detail when it serves a smaller audience.
Write plainly
- Put the answer or action near the beginning.
- Use common, concrete words. Explain a necessary technical or legal term in the same sentence.
- Address the reader as
you. Name the responsible organization when it acts. - Use active voice and strong verbs. Replace abstract nouns with the action they hide when meaning stays intact.
- Keep sentences focused. Split chains of conditions into bullets or separate cases.
- Use examples only when they clarify a rule. Label them as examples, not as the rule itself.
- State uncertainty, discretion, and possible outcomes honestly.
Structure the service content
- Use front-loaded, sentence-case headings that match words people would search.
- Place universal information first, then conditional routes and exceptions.
- Use numbered steps only for a required sequence.
- Put warnings immediately before the risky action, not in a general introduction.
- Make link text describe the action or destination.
- Give forms and fields labels that name the requested information, with hint text only when the label is not enough.
- End with the next action, alternative route, or source of help.
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.
- 9d ago First seen · 72 lines · 59 tokens per session scan A de9e043f491f
govuk is a skill published in the GitHub repository Neeeophytee/agent-stylebooks (59 stars, last pushed 17d ago), licensed MIT. It adds 59 tokens to every session and 704 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.