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 anaxite/agent-skills --skill ms-style-reviewergit clone --depth 1 https://github.com/anaxite/agent-skillsWrote 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/anaxite/agent-skills/ms-style-reviewer)<a href="https://agentmods.dev/skills/anaxite/agent-skills/ms-style-reviewer"><img src="https://agentmods.dev/badge/skills/anaxite/agent-skills/ms-style-reviewer/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/anaxite/agent-skills/ms-style-reviewer"><img src="https://agentmods.dev/badge/skills/anaxite/agent-skills/ms-style-reviewer.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 | $0.00093 | $0.02224 |
| Opus 5 | $0.00046 | $0.01112 |
| Sonnet 5 | $0.00019 | $0.00445 |
| Haiku 4.5 | $0.00009 | $0.00222 |
Grade A, and why
ms-style-reviewer 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 12d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Writing Style Guide - Review Skill
Review content against the Microsoft Writing Style Guide and report findings organized by severity.
Review workflow
1. Understand the content
Before reviewing, identify:
- Content type: documentation, UI text, blog post, developer/API docs, error messages, chatbot dialogue, procedures/instructions
- Audience: end users, developers, IT admins, general public
- Scope: full document, specific section, or single string
This determines which reference files to load. DO NOT load everything upfront.
2. Quick-scan pass
Read CHECKLISTS.md and scan the content against it. This catches the most common issues fast: capitalization, grammar, punctuation, word choice, acronym handling, numbers, formatting, procedures, and responsiveness.
Also read COMMON-TERM-PITFALLS.md and check whether the content uses any flagged terms.
2b. Term lookup
For any terms flagged in the quick scan—or any word that might be on the MSFT prohibited/preferred list—look up in the term index using grep:
grep -i ",term," references/TERM-INDEX-*.tsv
The index is split into four range files: TERM-INDEX-AD.tsv (A–D), TERM-INDEX-EL.tsv (E–L), TERM-INDEX-MS.tsv (M–S), TERM-INDEX-TZ.tsv (T–Z and symbols). The glob TERM-INDEX-*.tsv searches all four at once.
The match_variants column (column 2) uses leading and trailing comma delimiters for exact matching. Always search the match_variants column, not just the canonical column (column 1).
TSV columns: canonical | match_variants | file | type | thumbnail
- If the
thumbnail(column 5) resolves the question, record the finding and move on. - If the
typeisconditionalor the thumbnail indicates complexity, load the full entry from the letter file. Thefilecolumn gives the filename (e.g.,S.md):
What ships with it
58 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.
- references/A.md 15 KB
- references/ACCESSIBILITY.md 5.6 KB
- references/B.md 8.1 KB
- references/C.md 17 KB
- references/CAPITALIZATION.md 3.9 KB
- references/CHECKLISTS.md 8.7 KB
- references/COMMON-TERM-PITFALLS.md 7.5 KB
- references/D.md 11 KB
- references/DEVELOPER-CONTENT.md 7.9 KB
- references/E.md 14 KB
- references/F.md 11 KB
- references/FORMATTING.md 10 KB
- references/G.md 5.2 KB
- references/GLOBAL-READY.md 6.9 KB
- references/GRAMMAR.md 6.9 KB
- references/H.md 9.5 KB
- references/I.md 12 KB
- references/J.md 1.7 KB
- references/K.md 378 B
- references/L.md 8.3 KB
- references/M.md 14 KB
- references/N.md 4.3 KB
- references/NUMBERS-SYMBOLS.md 1023 B
- references/O.md 8.0 KB
- references/P.md 18 KB
- references/PROCEDURES.md 7.0 KB
- references/PUNCTUATION.md 9.5 KB
- references/Q.md 606 B
- references/R.md 12 KB
- references/S.md 17 KB
- references/T.md 8.5 KB
- references/TC-ACCESSIBILITY.md 2.7 KB
- references/TC-AI-BOT.md 5.2 KB
- references/TC-BIT-BYTE.md 2.5 KB
- references/TC-CLOUD-COMPUTING.md 6.4 KB
- references/TC-COMPUTER-DEVICE.md 6.5 KB
- references/TC-DATE-TIME.md 4.8 KB
- references/TC-KEYS-KEYBOARD.md 12 KB
- references/TC-MOUSE.md 3.8 KB
- references/TC-SECURITY.md 4.1 KB
- references/TC-SPECIAL-CHARS.md 8.5 KB
- references/TC-TOUCH-PEN.md 3.8 KB
- references/TC-UNITS.md 4.4 KB
- references/TERM-INDEX-AD.tsv 25 KB
- references/TERM-INDEX-EL.tsv 26 KB
- references/TERM-INDEX-MS.tsv 35 KB
- references/TERM-INDEX-TZ.tsv 13 KB
- references/U.md 8.8 KB
- references/V.md 2.9 KB
- references/VOICE-AND-TONE.md 6.0 KB
- references/W.md 3.0 KB
- references/WORD-CHOICE.md 3.7 KB
- references/X.md 849 B
- references/Y.md 473 B
- references/Z.md 1.2 KB
- scripts/download_style_guide.py 297 B runs code
- scripts/style_guide_downloader.py 8.9 KB runs code
- scripts/test_download_style_guide.py 319 B runs code
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.
- 12d ago First seen · 117 lines · 93 tokens per session scan A df8a3a93c8e5
ms-style-reviewer is a skill published in the GitHub repository anaxite/agent-skills (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 93 tokens to every session and 2,224 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
web-static
Build modern static websites using semantic HTML and CSS without external dependencies or build systems. Also owns the verification loop for such sites — drives the rendered pages through Chrome DevTools MCP (console, accessibility snapshot, viewport resize, dark/reduced-motion emulation, Lighthouse), executes the…
web-performance-reviewer
Review web frontends for performance issues by driving the rendered site through Chrome DevTools MCP — throttled performance traces, Core Web Vitals judged against thresholds, network waterfall analysis, and heap-snapshot leak checks for SPAs. Composes on top of web-static, web-sprinkles, or web-components. Strictly…
zcfg
Integrate zcfg (Zero Dependency Configuration Utility) into Java applications. Use when adding configuration loading, reading properties files, setting up application configuration, or integrating zcfg into a Java project. Triggers on "zcfg", "add configuration", "load properties", "application configuration with…
zcl
Add colored terminal output to Java applications using zcl (Zero-dependency Colour Logger). Use when adding colored console output, terminal logging with colors, ANSI color support, or integrating zcl into a Java project. Triggers on "zcl", "colored output", "colored logging", "terminal colors", "ANSI colors"…
zargs
Add zero-dependency argument parsing to Java CLI applications using the zargs pattern — an enum-based argument parser. Use when adding CLI argument parsing, command-line option handling, or adding options to a Java project. Triggers on "zargs", "argument parsing", "CLI arguments", "command-line options", "parse…
zunit
Generate and run zunit tests for java-cli-app projects. Use when asked to create tests, write tests, add tests, or generate test files for a java-cli-app project. Triggers on "zunit", "write tests", "create tests", "add tests", "test this", "generate tests", or requests to test a java-cli-app application. Also trigger…