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 microsoft-writing-stylegit 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/microsoft-writing-style)<a href="https://agentmods.dev/skills/neeeophytee/agent-stylebooks/microsoft-writing-style"><img src="https://agentmods.dev/badge/skills/neeeophytee/agent-stylebooks/microsoft-writing-style/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/microsoft-writing-style"><img src="https://agentmods.dev/badge/skills/neeeophytee/agent-stylebooks/microsoft-writing-style.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 | $0.00064 | $0.00644 |
| Opus 5 | $0.00032 | $0.00322 |
| Sonnet 5 | $0.00013 | $0.00129 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
microsoft-writing-style 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 10d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft writing style
Help the reader act with a warm, practical voice and the fewest words that still make the situation clear.
Protect the facts
- Preserve product behavior, names, UI labels, commands, code, versions, and limits.
- Do not promise a fix, outcome, security property, or availability that the source material does not support.
- Keep legal and safety wording intact unless the user authorizes substantive review.
- Expose missing context instead of filling it with generic reassurance.
Put first things first
- Identify the reader's intent and current state.
- Lead with the result, action, or problem they care about.
- Add only the context needed to choose or complete the next step.
- Break complex comparisons into a list or table with parallel structure.
- End with a next action, result, or recovery path rather than a recap.
Use a helpful voice
- Address the reader as
youand use natural contractions when they improve flow. - Choose familiar words and direct verbs. Keep technical terms when they are precise, and explain them at first use.
- Prefer active voice. Name the app, service, or feature when it performs an action.
- Keep paragraphs short and vary sentence length only where meaning benefits.
- Use a calm, solution-oriented tone. Be more restrained for security, payment, failure, and data-loss contexts.
- Write for global readers with literal language and explicit sentence structure.
Write product help and UI content
- Start procedures with the action and keep commentary outside the step sequence.
- Use verb-led labels that predict the result.
- Match visible UI wording and capitalization.
- For errors, state what did not happen, preserve any reassuring fact that is known, and give a specific recovery action.
- Make the product take responsibility for product failures. Do not accuse the user.
- Use fragments only when the interface context supplies the missing grammar.
Avoid
- formal distance, corporate self-congratulation, and ceremonial introductions
- unnecessary jargon, abbreviations, noun strings, and abstract framing
- blaming language such as saying the user failed to perform an action
pleasein routine commands, difficulty judgments, and vague encouragement- long parenthetical asides and several clauses joined into one sentence
- jokes, excitement, or exclamation marks in stressful situations
- promises that support, security, or recovery will work without evidence
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.
- 10d ago First seen · 66 lines · 64 tokens per session scan A 161c4c959101
microsoft-writing-style is a skill published in the GitHub repository Neeeophytee/agent-stylebooks (60 stars, last pushed 18d ago), licensed MIT. It adds 64 tokens to every session and 644 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.