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 tranfu-labs/tranfu-skills --skill tranfu-routergit clone --depth 1 https://github.com/tranfu-labs/tranfu-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/tranfu-labs/tranfu-skills/tranfu-router)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/tranfu-router"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/tranfu-router/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/tranfu-labs/tranfu-skills/tranfu-router"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/tranfu-router.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 | $0.00169 | $0.01322 |
| Opus 5 | $0.00084 | $0.00661 |
| Sonnet 5 | $0.00034 | $0.00264 |
| Haiku 4.5 | $0.00017 | $0.00132 |
Grade A, and why
tranfu-router 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 12d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tranfu-router
把用户对 tranfu-skills 公司库的 "搜 / 装 / 列 / 更新 / 卸载 / 诊断" 意图, 路由到本地 tfs CLI 命令. 你 (Claude Code / Codex CLI agent) 调 tfs 拿 JSON, 渲染给用户.
0. 版本预检 (HARD — 第一步, 早于任何其它 tfs 调用)
进 skill 第一件事, 不许跳:
- exec
tfs update --check-only --json, parse{self, skills, ...} - 判定落后 (任一为真):
self非 null 且self.status === "outdated"→ CLI 自身落后skills[]里有项目name === "tranfu-router"且status === "outdated"→ 本 skill 落后
- 任一落后:
- exec
tfs update --json(无 flag, 同时升 CLI + skill), parse 结果 - 给用户 1 行人话:
已升级: tfs CLI 0.5.0 → 0.6.0 / skill tranfu-router (sha A→B)(按实际填) - 中止本次流程, 给提示:
本 skill 文件刚被覆盖, 当前对话加载的仍是旧版. 请重新发一遍刚才的指令 (e.g. "搜 X / 装 X"), 让 agent 重新 trigger 加载新版. - NEVER 边升级边跑当前活 — 即便升级前已经解析出用户意图, 也不准跑后续 §1 之后任何步骤
- exec
- 全 noop /
self === null且 skills 里 router 不在 outdated → 进 §1
tfs update --check-only --json 走的是本地 cache + registry 拉取, 通常 < 2s. 即便慢也不许跳.
触发判断
接:
| 用户说 | 调 |
|---|---|
| "搜公司 skill 关于 X / tranfu-skills 有没有 X" | tfs search "X" --runtime=<self> --json |
| "公司库都有什么 skill / 列公司库 / list all" | tfs catalog --json |
| "装公司 skill X / 把 X 装到 user / project" | `tfs install X --scope=user |
| "我装了哪些公司 skill / 看本机 installed" | tfs installed --json |
| "更新公司 skill / 拉最新 / update" | tfs update --json |
| "卸载 X / uninstall X" | tfs uninstall X --runtime=<self> |
| "诊断 tfs / 检查环境" | tfs doctor --json |
不接 (留给 tranfu-publish skill):
- "发布本地 skill X / 推 X 到公司库"
- "推荐外部 skill 给公司库"
- "给公司库 skill X 加使用案例"
调 CLI 准则
-
显式 --runtime: 你知道自己是 Claude Code 还是 Codex CLI, 显式
--runtime=claude-code或--runtime=codex传, 避免 tfs 检测到双 runtime 时报runtime_required. -
用 --json: 支持 --json 的命令 (
search/catalog/list/installed/update/doctor) 加上, parse stdout 拿结构化结果渲染. install / uninstall 没 --json, 看成功的 stdout marker (✓) + 失败的 stderr JSON. -
错误解析: exit code 非 0 → stderr 永远是 JSON
{error, message, hint, exit_code}. parse 后把message+hint渲染给用户, 别原样吐 JSON 给用户看.
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.
- 12d ago First seen · 81 lines · 169 tokens per session scan A 68007bd56c14
tranfu-router is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 169 tokens to every session and 1,322 once invoked, about $0.0008 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…