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 briefgit 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/brief)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/brief"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/brief/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/brief"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/brief.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 | $0.00110 | $0.02170 |
| Opus 5 | $0.00055 | $0.01085 |
| Sonnet 5 | $0.00022 | $0.00434 |
| Haiku 4.5 | $0.00011 | $0.00217 |
Grade A, and why
article-workflow-brief 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Article Workflow Brief
这是流程类 Skill，默认仅在用户显式调用 $article-workflow-brief 时运行。
This is the first step in the article-workflow-* skill series, corresponding to Phase 0 of the article optimization workflow.
Goal: Organize an editorial Brief from oral drafts and outlines, helping the author confirm the article's thesis, target audience, main narrative thread, personal judgments, and evidence standards. The AI is an editorial assistant — it does not decide the author's final viewpoints for them. Decisions that require the author's input must be collected through dialog, not written into the final brief as unresolved items.
Trigger Scenarios
Use this skill when the user requests:
- Generate, organize, or update
.article-workflow/brief.md - Read
.article-workflow/sources/outline.mdand.article-workflow/sources/oral-draft/ - Generate an editorial brief based on oral drafts
- Execute Phase 0 of the article optimization workflow
- Collect user decisions through dialog and write them into the brief
Input and Output
Default inputs:
.article-workflow/sources/outline.md.article-workflow/sources/oral-draft/- Optional:
.article-workflow/sources/references/ - Optional:
.article-workflow/sources/proofs/
Default output:
.article-workflow/brief.md
If the user provides an article directory, look for .article-workflow/ inside it first. If the user only provides an oral draft directory, ask where the brief should be saved.
Core Principles
- Edit, don't ghostwrite.
- Do not rewrite the article body.
- Do not decide the author's final viewpoints for them.
- First identify questions that require the author's decision, collect the author's choices through dialog, then write the confirmed results into the brief.
- When encountering ambiguities that affect the thesis, audience, structural trade-offs, author judgments, or evidence standards, proactively use dialog to ask the user for confirmation — do not silently guess.
- The author makes judgments; the AI diagnoses, organizes, and executes.
- After each round's deliverable is complete, a sub-agent must be launched for alignment review; the sub-agent only offers review feedback, and the main agent decides whether to adopt it.
- Preserve the author's personal judgments, first-person experiences, viewpoint formation process, and distinctive voice.
- Technical details, evidence, and materials serve the article's main narrative only — do not turn the brief into a material dump.
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 eef6701b055a
- 8d ago Changed · +3 lines · +110 tokens per session fd9407fcfc3e
- 12d ago First seen · 233 lines · 0 tokens per session scan A 0a4f89a1bca3
article-workflow-brief is a skill published in the GitHub repository hxy91819/mason-skills (2 stars, last pushed today), licensed MIT. It adds 110 tokens to every session and 2,170 once invoked, about $0.0006 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…