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 spec-leak-reviewgit 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/spec-leak-review)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/spec-leak-review"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/spec-leak-review/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/spec-leak-review"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/spec-leak-review.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 | $0.00040 | $0.04532 |
| Opus 5.5 | $0.00016 | $0.01813 |
| Sonnet 5.5 | $0.00008 | $0.00906 |
| Haiku 4.5 | $0.00004 | $0.00453 |
Grade A, and why
spec-leak-review 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 1mo 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Leak Review
流程类 Skill,仅在用户显式调用 $spec-leak-review 时运行。默认审查后直接修复被审文件,再复验并生成 HTML,不询问是否修复或是否需要 HTML。用户明确要求只读时只审查;明确要求只要文字或不要 HTML 时改为 Markdown。先按对象的用途选择证据模式:
- 文本模式:长期规范、提示词、配置、日志、纯文本讲者备注等。以文件或用户提供的原文为证据,采集与定级无需浏览器或截图;生成 HTML 后仍验证报告的浏览器展示。
- 视觉模式:网站、网页应用、PPT/幻灯片(包括 HTML、PDF 或图片形式)及其中的比较页面。必须逐页真实看图,不能因为 HTML 可读源码而降为文本模式。用目标格式的渲染工具获取画面;用户提供的截图也可作为已覆盖部分的证据。
混合输入分别记录,例如幻灯片走视觉模式、独立备注走文本模式。报告开头写明模式、输入版本/哈希、实际页数/界面状态、受众和覆盖范围。视觉采集失败时保持视觉模式并记录缺口。默认通过 $review-html-report 生成单文件 HTML,保留审查记录与视觉采集、标注截图。
1. 确定受众与决策
先回答三件事并写进报告开头:谁会阅读或打开目标;带着什么疑问来;看完之后要做出什么决定或动作。文本模式中的“受众”可以是执行该文档的 agent、维护 Skill 的作者或文档读者;视觉模式中的“受众”是页面用户或演讲观众。
受众决定一切判定——同一句“清单摘要 975d85…”对终端用户是噪音,对值班运维是工作对象。无法从用户输入、目标文件、网站上下文或代码判断受众时,先问用户,不要假设后展开审查。
完成标准:受众和“看完要做的决定”各能用一句话说清,且后续每条 finding 都能挂回其中一句。
2. 建立证据清单
文本模式
逐个读取用户指定的文本;没有指定文件时,只扫描任务范围内的文本,不把二进制或依赖目录当成证据。保留原文、文件路径和行号(必要时给出段落或字符范围),并记录文件用途、预期读者和是否由配置/模板生成。多文件交叉引用时以实际引用链为准,不凭目录名推断。
重点标出这些提示词残留:面向模型的会话开场、角色扮演、一次性用户请求、对当前对话的指代、隐藏推理或“请先……再……”的临时编排、把宿主/调用方式复述进正文的元说明,以及与文档任务无关的用户背景。提示词语气本身不是问题:Skill 的操作步骤、约束和安全门槛只要服务于预期读者,就属于正文。
完成标准:每个被审文件都有用途、读者、覆盖行数和证据位置;每条 finding 都能回指原文行号或明确标注为用户提供的片段。
视觉模式
双轨采集,两轨都有时交叉核对。
截图轨:用 scripts/capture-surface.js 或目标格式渲染器采集每个页面/幻灯片。脚本生成真实截图、文档坐标 bbox 的 DOM 文本清单及 surfaces 绘制面清单;后者包括图片、canvas、SVG、背景图、嵌入页等需单独看图的区域,不含位图文字识别。title/aria-label 属于辅助属性,不能直接当作当前画面已显示的文案。脚本非零退出、错误页、失败图片都要记录缺口;采集成功也不代表完成审查。
真正打开每一张截图看图,按区域盘点标题、副标题、说明、卡片、字段、状态、按钮及位图内文。surfaces 是补充盘点入口;图中存在而清单未捕获的区域(如 iframe 内部、伪元素或复杂合成)手工补入。对每个承载文字/证据的位图记录截图/素材、页与 bbox、实际读到的原文及用途;alt、OCR 和 DOM 清单只作线索,须回图核对。不可辨认处记录范围与原因,不凭上下文补写。
在实际投影视口看整页,再看重要局部。逐页记录已打开的图、视口、具体观察、位图覆盖及缺口;关键制作说明或证据不能因小字而免审。拿不到浏览器时可以使用用户已有截图,未覆盖的页/状态仍保留在总数中。
代码轨:用截图里的文案原文在仓库检索定位组件与 i18n 条目,比按目录猜更可靠;每条给出 file:line。截图未出现的错误态、空态、tooltip、loading 等分支文案一并纳入清单。文案有配置或环境变量覆盖机制时,确认线上生效值,不拿源码默认值当结论。
截图里有而代码里检索不到的,标注来源为运行时数据或后端返回。部分区域因鉴权、外部网关或无法构造触发条件而采集不到时,如实记录范围和原因,不用源码推断冒充渲染结果。
对展开、tooltip、幻灯片导航、比较切换等无写入交互,实际操作后再看图并记录步骤、状态与结果;嵌入画面的真实内容和图注/结论是否对应一并核对。不能安全触发的状态记未覆盖,不根据控件存在推定完成。
What ships with it
4 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.
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.
- 1mo ago Changed · +2 lines 4e363f2785bf
- 1mo ago Changed · +12 lines 7ce0e7562e7a
- 1mo ago Changed · +15 lines · -20 tokens per session f53d5e6556e3
- 1mo ago Changed · +2 lines bc4eda16fdd8
- 2mo ago First seen · 106 lines · 60 tokens per session scan A 76d4b0c5a25a
spec-leak-review is a skill published in the GitHub repository hxy91819/mason-skills (3 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 4,532 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.
spec-leak-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| spec-leak-reviewhxy91819/mason-skills | Skill | 3 | today | MIT | A | 40 | Claude Code, Codex |
| webgl-holographic-foilnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | today | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | 2d ago | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | yesterday | MIT | A | 47 | Claude Code |