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.
git 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/commands/tranfu-labs/tranfu-skills/prerequisites)<a href="https://agentmods.dev/commands/tranfu-labs/tranfu-skills/prerequisites"><img src="https://agentmods.dev/badge/commands/tranfu-labs/tranfu-skills/prerequisites/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/commands/tranfu-labs/tranfu-skills/prerequisites"><img src="https://agentmods.dev/badge/commands/tranfu-labs/tranfu-skills/prerequisites.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 | $0.00000 | $0.01762 |
| Opus 5 | $0.00000 | $0.00881 |
| Sonnet 5 | $0.00000 | $0.00352 |
| Haiku 4.5 | $0.00000 | $0.00176 |
Grade A, and why
prerequisites scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `gh / jq / curl / git / base64` 任一缺 | `brew install <tool>` (macOS) 或对应平台包管理器 | How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 0：preflight 索引（人话说明）
reconcile flow 的 Step 0 只做一件事：跑 ../assets/preflight.sh。本文档是脚本的「人话伴侣」——脚本里每条 check 的语义、失败的修复路径、为什么这样设计。脚本本身是 single source of truth，本文档落后于脚本时以脚本为准。
工作单元契约
-
输入：当前 shell 环境（
$COOLIFY_API_TOKEN+ghtoken）+ 当前 git 仓库 + 当前 cwd -
输出：退出码 0 / 1 / 2 + stdout 上的逐条 ✓ / ✗ / ⚠ + 6 个公共变量（agent 解析输出拿）：
$BASE = http://120.77.223.183:8000 $SERVER_UUID = oz7r53ilv7aeaubx7ewuqw0m $GITHUB_APP_UUID = <preflight 从 /api/v1/github-apps 拿> $REPO_ORG = tranfu-labs $REPO_NAME = <user-repo> $APP_NAME = $REPO_NAME -
完成判据：脚本退出码 0
-
Ownership：read-only。脚本任一硬 check 失败 → 输出原文 + 退出码 1。MUST NEVER：自动装工具、自动建 repo、自动跳过断言
怎么跑
# 在目标项目根目录跑
bash <SKILL_ROOT>/assets/preflight.sh
# 或显式指定 base url
bash <SKILL_ROOT>/assets/preflight.sh http://120.77.223.183:8000
<SKILL_ROOT> = 本 skill 安装路径，通常是 ~/.claude/skills/own-skills/tranfu-coolify-ops/ 或 worktree 里的 .claude/worktrees/.../own-skills/tranfu-coolify-ops/。
退出码
| 退出码 | 含义 | 下一步 |
|---|---|---|
0 |
全 ✓ | 进 reconcile Step 2 |
1 |
任一硬 check ✗ | 终止，按脚本输出的 ✗ <reason> 修完再跑 |
2 |
仅 ⚠（如 GHCR credential 未 ack） | 去 Coolify UI 配 ghcr.io credential，回来 ack 重跑 |
check 清单 + 失败修复路径
按脚本输出顺序：
▸ 工具
| ✗ 原因 | 修 |
|---|---|
gh / jq / curl / git / base64 任一缺 |
brew install <tool> (macOS) 或对应平台包管理器 |
▸ Git 仓库状态
| ✗ 原因 | 修 |
|---|---|
| 当前 cwd 不在 git 仓库 | cd 到项目根目录 |
| 无 origin remote | git remote add origin <url> |
org ≠ tranfu-labs |
不修——本 skill 只服务 tranfu-labs 仓库；如确需扩展先讨论再改 skill |
| 命名不合规（不是 烤肉串-app 全小写） | 改 repo 名（GitHub UI → Settings → General → rename），同步本地 git remote set-url origin ... |
| working tree dirty | git stash 或 git commit 当前改动 |
▸ GitHub 凭据
| ✗ 原因 | 修 |
|---|---|
gh 未 auth |
gh auth login |
token scope 缺 'repo' |
gh auth refresh -s repo |
| 用户对 repo 无 admin permission | 让 repo owner 把你加为 admin collaborator（Settings → Collaborators） |
| repo 不存在 / 网络问题 | 检查 origin URL 拼写 / VPN |
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 First seen · 125 lines · 0 tokens per session scan A e16bb4cbc9a0
prerequisites is a command published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,762 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
fix
Universal debugging and fix application with semantic code analysis.
doctor
Badi configuration validation. Checks all Badi components and produces a diagnostic report.
http-service
Build, review or debug a Bun HTTP service. Loads the http-service skill, then works the task through its workflow.
gh-issue-use-cypress
Like /gh-issue-use-browser, but pinned to the Cypress MCP — use when your project runs the Cypress MCP for browser automation. Example — /gh-issue-use-cypress "Composer > Save" saving toasts failure but the record persists.