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 clean-sourcesgit 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/clean-sources)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/clean-sources"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/clean-sources/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/clean-sources"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/clean-sources.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 | $0.00081 | $0.02562 |
| Opus 5 | $0.00041 | $0.01281 |
| Sonnet 5 | $0.00016 | $0.00512 |
| Haiku 4.5 | $0.00008 | $0.00256 |
Grade A, and why
article-workflow-clean-sources 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Article Workflow Clean Sources
这是流程类 Skill,默认仅在用户显式调用 $article-workflow-clean-sources 时运行。
This is Phase 0.5 of the article-workflow-* skill series, corresponding to "oral draft cleaning" in the article optimization workflow overview.
Goal: first correct obvious errors introduced by oral transcription, preventing downstream structural reviews from being disrupted by transcription mistakes. AI only performs cleaning — no polishing, rewriting, structural changes, or opinion processing. The author makes the final call on terminology, style, and uncertain items.
Trigger Scenarios
Use this skill when the user requests:
- Referencing Phase 0.5 to clean oral drafts
- Organizing, cleaning, or correcting
.article-workflow/sources/oral-draft/ - Generating
.article-workflow/00-cleaned-sources/ - Standardizing proper nouns, capitalization, and obvious transcription errors in oral drafts
- Recording terminology questions or uncertain items from oral draft cleaning
Input and Output
Default input:
.article-workflow/sources/oral-draft/.article-workflow/brief.md
Default output:
.article-workflow/00-cleaned-sources/*.md: cleaned oral draft text, saved under the original filenames.article-workflow/00-cleaned-sources/terminology-notes.md: proper noun corrections, uncertain items, and cleaning boundary records
If the user provides an article directory, first look for .article-workflow/ within that directory. If brief.md is missing, ask whether to proceed; without a brief, only basic transcription cleaning can be done — do not infer the article's terminology system on your own.
Core Principles
- Clean, not polish.
- Preserve the author's speaking style, sentence patterns, tone, and order of ideas.
- Only correct obvious typos, speech recognition errors, proper noun capitalization and spelling, clearly redundant filler words, and basic spacing between Chinese and English text.
- Do not restructure sentences, replace the author's word choices, optimize expressions, delete ideas, or add content.
- Terminology notes are intermediate artifacts, always using
terminology-notes.md, to avoid being mistaken for article body text in later phases. - When uncertain about proper nouns, facts, colloquial style boundaries, or cleaning strategies that affect whole-document consistency, do not guess — proactively ask the author to confirm via dialog before writing into the cleaned draft.
- Terminology notes record confirmed treatments and a small number of low-risk doubtful points; they do not replace proactive confirmation.
- Blockquotes, code blocks, and original excerpts are kept as-is by default, unless the user explicitly requests synchronized corrections.
- By default, standardize
issue/issuesin body text toIssue/Issues, but do not change blockquotes, code blocks, or original excerpts by default. - After each round of output, a sub-agent must be launched for goal-alignment review; 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.
- 7d ago Changed · +3 lines · +81 tokens per session 996373026b41
- 11d ago First seen · 224 lines · 0 tokens per session scan A 02850d1cb421
article-workflow-clean-sources is a skill published in the GitHub repository hxy91819/mason-skills (2 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 2,562 once invoked, about $0.0004 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…