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 st1page/agent-knowledge-framework --skill installable-skill-hygienegit clone --depth 1 https://github.com/st1page/agent-knowledge-frameworkWrote 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/st1page/agent-knowledge-framework/installable-skill-hygiene)<a href="https://agentmods.dev/skills/st1page/agent-knowledge-framework/installable-skill-hygiene"><img src="https://agentmods.dev/badge/skills/st1page/agent-knowledge-framework/installable-skill-hygiene/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/st1page/agent-knowledge-framework/installable-skill-hygiene"><img src="https://agentmods.dev/badge/skills/st1page/agent-knowledge-framework/installable-skill-hygiene.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 | $0.00076 | $0.00932 |
| Opus 5.5 | $0.00030 | $0.00373 |
| Sonnet 5.5 | $0.00015 | $0.00186 |
| Haiku 4.5 | $0.00008 | $0.00093 |
Grade A, and why
installable-skill-hygiene 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.
What it actually says
Installable Skill Hygiene（发布质量与引用卫生）
目标：让 installable-skills/<skill-name>/ 安装后仍然可用（不依赖原仓库布局/当前工作目录），并且可维护（变更可 review、可回滚）。
核心约束（必须）
- 自包含：skill 安装后只应依赖
installable-skills/<skill-name>/目录内的文件。 - 禁止"逃逸路径"：
SKILL.md（以及被它引导打开的文件）不得引用../等跳出 skill 根目录的路径；不得要求读base/、roles/、仓库根README.md这类"在原仓库里存在、安装后可能不存在"的路径。 - 入口可读：
SKILL.md里要能让读者在不打开别的文件的情况下理解"要做什么 + 怎么做 + 何时触发"。
发布口径（两种都允许，选其一）
A）单文件口径（最稳）
把必要内容尽量内嵌在 SKILL.md。适用于：
- skill 短小、步骤清晰
- 不希望出现任何跨文件引用（包括
references/...）
代价：SKILL.md 会变长，维护时更容易出现"改一点动全篇"。
B）skill 内部引用口径（更可维护）
允许使用 skill 目录内部 的相对引用，例如：
references/...scripts/...assets/...
适用于：
- 需要附带 API 参考/长文档/示例配置
- 需要脚本提高确定性
注意：这里的"相对路径"只允许 相对于 skill 根目录 的内部路径；不要出现任何 ../ 逃逸。
发布前检查（推荐顺序）
1）front matter 基本校验（YAML）
如果本机有 skill-creator 的 quick_validate.py，优先跑：
python <path-to-skill-creator>/scripts/quick_validate.py installable-skills/<skill-name>
2）引用闭包扫描（禁止逃逸 + 禁止仓库根依赖）
在 skill 目录下扫一遍可疑引用（按需加关键字）：
rg -n "(^|\\s)(\\.\\./|/base/|\\broles/|\\binstallable-skills/\\b|README\\.md\\b|AGENTS\\.md\\b)" -S installable-skills/<skill-name>
解释：
../：大概率是"逃逸路径"base/、roles/：大概率是"依赖原仓库布局"installable-skills/：skill 内不应再写全局路径（安装后不稳定）README.md、AGENTS.md：常见误指向仓库根文件（除非它们位于 skill 目录内）
3）安装体验抽查（可选）
在仓库的 installable-skills/ 目录下执行：
npx skills add . --skill='<skill-name>' -g -y
Escalate to experience if
- 安装后出现坏链接/缺文件，但在原仓库里"看起来没问题"
- 需要同时维护 internal/public 两个仓库的 installable skills，且希望 diff 可控
- 文档附录对比出现"附录 diff 远大于正文"的异常现象
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 First seen · 82 lines · 76 tokens per session scan A d3dbf06dcc51
installable-skill-hygiene is a skill published in the GitHub repository st1page/agent-knowledge-framework (41 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 76 tokens to every session and 932 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…