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 wenhaochai/claude-plugins --skill stylegit clone --depth 1 https://github.com/wenhaochai/claude-pluginsWrote 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/wenhaochai/claude-plugins/style)<a href="https://agentmods.dev/skills/wenhaochai/claude-plugins/style"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/style.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02996 |
| Opus 5 | $0.00000 | $0.01498 |
| Sonnet 5 | $0.00000 | $0.00599 |
| Haiku 4.5 | $0.00000 | $0.00300 |
Grade A, and why
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 7d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Style
Default standards for English prose. Apply at generation and edit time. All rules are peers; no group is higher priority than another.
Scope. RULE-01..17 apply to every writing task: email, message draft, post, doc, paper prose. RULE-P1..P18 apply only when the target is a page-capped paper (NeurIPS/ICML/ICLR-style 8-10 page caps and similar); skip them for email and short-form prose where they would over-constrain tone. RULE-A1..A2 are final-pass audit rules: trigger only when reviewing the compiled PDF for submission, not during drafting.
Canonical (RULE-01..17)
RULE-01..12 distilled from Strunk & White, Orwell, Pinker, and Gopen & Swan. RULE-13..17 added by Wenhao Chai.
- RULE-01 Do not assume the reader shares your tacit knowledge. (Pinker 2014, Ch. 3)
- RULE-02 Do not use passive voice when the agent matters. (Orwell 1946 Rule 3; S&W §II.14)
- RULE-03 Do not use abstract or general language when a concrete, specific term exists. (S&W §II.16; Pinker 2014 Ch. 3)
- RULE-04 Do not include needless words. (S&W §II.17; Orwell 1946 Rule 3)
- RULE-05 Do not use dying metaphors or prefabricated phrases. (Orwell 1946 Rule 1)
- RULE-06 Do not use avoidable jargon where an everyday English word exists. (Orwell 1946 Rule 5; Pinker 2014 Ch. 2)
- RULE-07 Use affirmative form for affirmative claims. (S&W §II.15)
- RULE-08 Do not linguistically overstate or understate claims relative to the evidence. (Pinker 2014 Ch. 6; Gopen & Swan 1990)
- RULE-09 Express coordinate ideas in similar form (parallel structure). (S&W §II.19)
- RULE-10 Keep related words together. (S&W §II.20; Gopen & Swan 1990)
- RULE-11 Place new or important information in the stress position at the end of the sentence. (Gopen & Swan 1990)
- RULE-12 Break long sentences; vary length. Split sentences over 30 words. (S&W §II.18; Pinker 2014 Ch. 4)
- RULE-13 Do not use em-dashes (
—in prose,---in LaTeX) or prose parentheses()in body text. Use colons plus lists,, namely ...,, where ..., or new sentences instead. Math parentheses (ordered pairs, function application, set notation) and page-range en-dashes (pp.~12--15) are exempt. - RULE-14 Do not use vocabulary that signals LLM-generated prose. Common tells: "delve", "crucially", "multifaceted", "tapestry", "navigate the complexities", "in the realm of", "leverage" where "use" suffices, "moreover"/"furthermore" chains, em-dash sandwiches. If a phrase pattern-matches GPT default, swap for a plainer equivalent.
- RULE-15 Be consistent within a single piece. Define an abbreviation on first use, then never re-expand. Once you pick italic vs roman "e.g.", "GPT-5-thinking" vs "GPT-5 (thinking)", a hyphenation convention, or a math-mode policy, hold it. Inconsistency reads as careless.
- RULE-16 Do not use the same content word twice in one sentence or in adjacent sentences. Restructure, pronominalize, or pick a role-specific alternative. Function words and the piece's named signature concepts are exempt; reusing a defined term is desirable, not a violation.
- RULE-17 Do not apologize in body prose for weak assumptions, narrow scope, or worse-than-baseline results. State each assumption once where it belongs and reserve limitations for a dedicated section. Phrasings like "Although our algorithm does not outperform X" frame weakness without communicating it; cut them.
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.
- 7d ago First seen · 97 lines · 0 tokens per session scan A 9ccddee8c152
style is a skill published in the GitHub repository wenhaochai/claude-plugins (16 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,996 tokens. 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…