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 SSBun/csl-agent-kit --skill integrate-third-skillsgit clone --depth 1 https://github.com/SSBun/csl-agent-kitWrote 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/ssbun/csl-agent-kit/integrate-third-skills)<a href="https://agentmods.dev/skills/ssbun/csl-agent-kit/integrate-third-skills"><img src="https://agentmods.dev/badge/skills/ssbun/csl-agent-kit/integrate-third-skills.svg" alt="Measured on agentmods" 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 | $0.00097 | $0.01080 |
| Opus 5 | $0.00048 | $0.00540 |
| Sonnet 5 | $0.00019 | $0.00216 |
| Haiku 4.5 | $0.00010 | $0.00108 |
Grade A, and why
integrate-third-skills 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
集成第三方技能
将需要维护的上游技能作为 CSL Agent Kit 的源码导入,而不是安装到全局目录。此流程仅位于当前仓库的 .agents/skills/integrate-third-skills/,不会随共享 skills/ 分发、全局 Codex symlink 安装或 Pi 命令发现。每个导入技能保留可复现的上游基线,因此后续可以安全比较更新并保留本地修改。
触发边界由 evals/trigger_cases.json 和 evals/semantic_config.json 覆盖。
流程
-
检查用户给出的仓库链接:确认许可证、默认分支或 tag、可用叶子技能(含
SKILL.md)及上游目录路径。未明确选择技能时,先列出候选并等待用户选择;不要默认导入整个仓库。 -
规划目标:放在
skills/<来源分组>/<技能名>/。来源分组优先使用用户指定名称;未指定时,使用 GitHub owner(若与现有来源冲突则改为owner-repo)。同一来源的许可证放在skills/<来源分组>/LICENSE。 -
导入所选叶子目录的全部必要文件,并在每个含
SKILL.md的第三方叶子目录写入.repository.json:{ "repository": "https://github.com/owner/repository", "sourcePath": "上游仓库内的相对路径", "ref": "导入时的分支或 tag", "commit": "导入时解析到的完整 Git commit", "license": "上游许可证标识或 Unknown", "upstreamStatus": "active | deprecated | unknown" } -
先检查本仓库递归发现的所有技能名。若名称冲突,展示来源与差异,并要求用户明确选择替换、重命名或跳过;不得静默覆盖。已有导入技能更新时,先比较上游与本地修改,确认后才覆盖或合并。
-
仅在现有发现机制无法识别新布局时修改 CLI/Pi 发现逻辑。同步更新 README 技能表、技能数量和第三方来源说明。
-
添加或更新回归测试,至少验证每个第三方叶子都有可解析的
.repository.json,且 CLI 与 Pi 能发现新技能。 -
Validation: as permitted by the current user and project rules, run
npm run check,npx skills add . --list --full-depth,npm pack --dry-run --json, andgit diff --check; then run the repository's built-in$skill-qualitygate for every changed Skill package. Unless the user explicitly requests it, do not run the real installer, modify~/.agents/skills, publish, or push.
检查已有来源
运行附带的只读 Git 子命令;它们只读取本地 vendor 目录,并使用临时目录获取上游,不会更新任何技能:
# 检查每项技能源路径导入后是否发生上游变化
node .agents/skills/integrate-third-skills/scripts/third-party-skills.js status
# 显示某项技能的上游变化和本地副本差异摘要
node .agents/skills/integrate-third-skills/scripts/third-party-skills.js diff SKILL_NAME
# 需要逐行补丁时才追加 --patch
node .agents/skills/integrate-third-skills/scripts/third-party-skills.js diff SKILL_NAME --patch
status 使用 .repository.json 的 repository、ref 与 commit;diff 还会从该 ref 检出上游并分别展示“导入后上游变化”和“当前上游对本地副本的差异”。对其他工作区可追加 --skills-root <path>。无法访问远端、缺少 Git、名称不唯一或元数据损坏时停止并报告,不猜测或覆盖文件。
What ships with it
3 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.
- 7d ago First seen · 56 lines · 97 tokens per session scan A ef5d030fe6fa
integrate-third-skills is a skill published in the GitHub repository SSBun/csl-agent-kit (10 stars, last pushed 5d ago), licensed MIT. It adds 97 tokens to every session and 1,080 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…