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-publishgit 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-publish)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/tranfu-publish"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/tranfu-publish/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-publish"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/tranfu-publish.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 | $0.00139 | $0.03227 |
| Opus 5 | $0.00069 | $0.01614 |
| Sonnet 5 | $0.00028 | $0.00645 |
| Haiku 4.5 | $0.00014 | $0.00323 |
Grade B, and why
tranfu-publish scanned grade B with 1 finding 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 9d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
- **own**: 用户本地目录 (原话 / `find ~/.claude/skills -name <name>`) How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tranfu-publish
把本地写的 / 推荐的 skill / 案例发到公司库 (tranfu-labs/tranfu-skills) 走 PR。触发即发布: 识别意图 → 起草所有内容 → 自动 push + 开 PR, 中途不打印预览、不等用户拍板。
参考 README.md 看框架图 / 路径概览。本 SKILL.md 是完整步骤 + Hard rules。
触发判断
| 用户说 | path | 产物 |
|---|---|---|
| "发布本地 skill X 到公司库" | own | own-skills/<name>/{SKILL.md, README.md, ...} |
| "推荐这个外部 skill (https://...) 到公司库" / "把这个 skill 推到公司库" | external | external-skills/<name>/{SKILL.md(薄指针), README.md}, skill body 不进库 |
| "给公司库 X 加使用案例 / 补一个用法" | case | 在 <own|external>-skills/<name>/cases/<recommender>.md 追加 / 新建 |
files 必备清单 (缺 = 中止, 不蒙混):
| variant | SKILL.md | README.md | cases/ |
|---|---|---|---|
| own | 必须 | 可选 (源里有就一起带, 没有不强求) | 可选 (源里有就一起带, 没有不强求) |
| external | 必须 (薄指针) | 必须 (AI 起草) | 不需要 |
| case | 不动 | 不动 | 必须 (新建或 append) |
多 skill 一次发: 上游仓库 / 本地路径含 ≥2 个 skill (≥2 个 SKILL.md, 或 .md frontmatter 含 name:) → 自动全收, 一个 PR 多目录 / 多 commit, 不让用户选。
不接 (留给 tranfu-router): search / install / list / installed / update / uninstall / doctor。
模板 (templates/ — 渲染必用, 不自创结构)
| 文件 | 用途 | 用于 |
|---|---|---|
templates/pr-body.md |
PR body 骨架, 含 own/external/case 三段 | 三路径 |
templates/case-file.md |
case 文件骨架, frontmatter + 4 段 body | case |
templates/section-同类对比.md |
README.md ## 同类 Skill 对比 段 |
external |
templates/section-使用技巧.md |
README.md ## 使用技巧 段 |
external |
README 的 ## 同类 Skill 对比 / ## 使用技巧 段名照 templates/ 保持一致 (catalog + 人读的约定, 别换成 ## Summary 之类)。PR body 怎么写无所谓 —— CI / 飞书通知都只把 body 原样转发, 不解析段名。
标准流程
进 skill 第一件事, CREATE A TODO LIST FOR THE TASKS BELOW (每步一个 TODO, 起步即建, 非可选): §0 版本预检 / §1 定位 $REPO+$SRC / §2 识别 path / §3 起草内容 / §4 起草 PR title+body / §5 提交+开 PR。
0. 版本预检 (HARD — 早于一切)
进 skill 第一件事:
- exec
tfs update --check-only --json, parse{self, skills, ...} - 判定落后 (任一为真):
self.status === "outdated"; 或skills[]中name === "tranfu-publish"且status === "outdated" - 任一落后 → exec
tfs update --json(同升 CLI + skill), 给用户 1 行 (已升级: tfs X→Y / skill tranfu-publish sha A→B), 然后中止本轮:
NEVER 边升级边跑后续步骤。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发布意图, 让 agent 重新 trigger 加载新版。 - 全 noop → 进 §1。
What ships with it
7 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.
- 9d ago Changed 0137ae1a12e6
- 12d ago First seen · 172 lines · 139 tokens per session scan B 3832d472d88d
tranfu-publish is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 139 tokens to every session and 3,227 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…