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 hxy91819/mason-skills --skill style-biblegit clone --depth 1 https://github.com/hxy91819/mason-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/hxy91819/mason-skills/style-bible)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/style-bible"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/style-bible/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/hxy91819/mason-skills/style-bible"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/style-bible.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 | $0.00104 | $0.02662 |
| Opus 5 | $0.00052 | $0.01331 |
| Sonnet 5 | $0.00021 | $0.00532 |
| Haiku 4.5 | $0.00010 | $0.00266 |
Grade A, and why
article-workflow-style-bible 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 today.
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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Article Workflow Style Bible
这是流程类 Skill,默认仅在用户显式调用 $article-workflow-style-bible 时运行。
This is Phase 5.0 of the article-workflow-* skill series.
Goal: Before entering multi-round polishing, distill a style bible from the main draft and Brief that describes the writing fingerprint the author wants to preserve. The AI does the distillation and organization; the author confirms and corrects. Every subsequent Phase 5 polish round must read it as a constraint baseline.
Trigger Scenarios
Use this skill when the user requests:
- Execute the preliminary step of Phase 5 of the article optimization workflow
- Generate a style bible / style fingerprint
- Prepare a constraint document for multi-round polishing
- Extract writing style from the main draft and organize it into citable rules
- Generate
.article-workflow/style-bible.md
Input and Output
Default input:
.article-workflow/04.5-main-draft/main-draft.md(the main draft after Phase 4.5 integration, for observing the author's actual writing fingerprint).article-workflow/brief.md(Phase 0 editorial Brief, to cross-reference confirmed direction, attitude, and author judgments)- Optional:
.article-workflow/sources/oral-draft/(to sense the original spoken style) - Optional:
.article-workflow/00-cleaned-sources/terminology-notes.md(confirmed proper noun conventions)
Default output:
.article-workflow/style-bible.md
If a previous project already has .article-workflow/05-polish-rounds/style-bible.md, read it for reference, but write the new artifact to the root-level .article-workflow/style-bible.md by default, to avoid confusion with Phase 5 round artifacts.
Core Principles
- Extract patterns from real text; do not invent definitions. Every "author characteristic" must be traceable to a corresponding passage in the main draft.
- Do not treat "general standards of good writing" as style: distinguish between "good Chinese" and "this author's Chinese."
- Positive descriptions (what to preserve) and negative lists (what to forbid) are equally important. Negative lists often have stronger binding force on subsequent agents.
- Proper nouns, terminology, and formatting conventions must be precise enough for mechanical checking.
- No-change zones must cover: rhetorical-question progression, short-sentence judgments, colloquial connectors, turning-point rhythms, and personal reflections in closing paragraphs — these are the tone carriers most easily deleted by mistake during polishing.
- Clearly distinguish "trimmable" from "untouchable": list trimmable content types as well, to prevent subsequent polishing from going to either extreme (change nothing vs. change everything).
- When encountering ambiguities that would affect the overall polishing direction (e.g., whether a class of tone words belongs to the author's voice or is redundant, whether the author intentionally uses a certain type of expression), proactively use
AskQuestionto ask the author to confirm; if the main draft's characteristics are clear and ambiguities are few, do not force questions just for form's sake. - After the artifact is written, a sub-agent review must be launched; the sub-agent only provides review opinions, and the main agent decides whether to adopt them.
What ships with it
1 file 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.
- today Changed · +2 lines 376d62f2d61b
- 8d ago Changed · +3 lines · +104 tokens per session b8369fe777a1
- 12d ago First seen · 203 lines · 0 tokens per session scan A e62253a08d44
article-workflow-style-bible is a skill published in the GitHub repository hxy91819/mason-skills (2 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 2,662 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
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…