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/deploy-trigger)<a href="https://agentmods.dev/commands/tranfu-labs/tranfu-skills/deploy-trigger"><img src="https://agentmods.dev/badge/commands/tranfu-labs/tranfu-skills/deploy-trigger/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/deploy-trigger"><img src="https://agentmods.dev/badge/commands/tranfu-labs/tranfu-skills/deploy-trigger.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 | $0.02646 |
| Opus 5.5 | $0.00000 | $0.01058 |
| Sonnet 5.5 | $0.00000 | $0.00529 |
| Haiku 4.5 | $0.00000 | $0.00265 |
Grade A, and why
deploy-trigger 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl POST $BASE/api/v1/deploy?uuid=<application-uuid> How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
部署触发链路
reconcile Step 7 / Step 8 用。
链路总览
git push -> GitHub Actions deploy.yml -> docker build -> push GHCR (rolling tag + sha tag)
↓
PATCH /applications/$APP_UUID/envs IMAGE_REF=ghcr.io/<org>/<repo>:sha-<commit>
↓
curl POST $BASE/api/v1/deploy?uuid=<application-uuid>
↓
Coolify (Application + dockercompose) 读取 IMAGE_REF -> pull immutable sha tag -> up
Coolify Application 创建时 is_auto_deploy_enabled=false——GitHub push 不触发 Coolify 自动部署, 触发权完全归 GHA workflow。即便 Coolify GitHub App integration 会订阅 GitHub push webhook, 因为 auto_deploy 关了, Coolify 收到 push 也不动。
GitHub 端配置(reconcile Step 5I)
Repo-level secrets
# strip 尾斜杠防 //api 404
gh secret set COOLIFY_API_TOKEN --body "$COOLIFY_API_TOKEN"
gh secret set COOLIFY_BASE_URL --body "${BASE%/}"
注意命令字符串里只能引用 $COOLIFY_API_TOKEN,不能把 token 原文写进去——shell 展开发生在执行时,命令字符串本身(agent 写给 Bash tool 的字符串)必须保持 $VAR 不变。
校验是否已设:
gh secret list | grep -E '^COOLIFY_API_TOKEN|^COOLIFY_BASE_URL'
自动建 environment(gh api 直通 REST API)
gh CLI 子命令没有 create environment,但 REST API 支持。reconcile Step 5I 用:
gh api -X PUT "repos/$REPO_ORG/$REPO_NAME/environments/$DEFAULT_BRANCH" >/dev/null
- 是 PUT 不是 POST — idempotent,已存在不报错
- 空 body 即可(不需要配 reviewers / wait_timer 之类)
- 需要 token 有
reposcope + admin permission(preflight Step 0 check 过)
Environment-level vars(每个部署分支一个同名 environment)
默认分支(如 main):
gh variable set COOLIFY_APP_UUID --env main --body "<application-uuid>"
gh variable set IMAGE_TAG_ROLLING --env main --body "latest"
# IMAGE_TAG_SHA_PREFIX 可省略;deploy.yml.template 默认使用 sha-,避免 GitHub env var 空值 422。
# 如要显式配置,也必须非空:
gh variable set IMAGE_TAG_SHA_PREFIX --env main --body "sha-"
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 · 230 lines · 0 tokens per session scan A 4fbbe4c2c43b
deploy-trigger is a command published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,646 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
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
validate-pr-description
Use when validating a PR title and description for conventional commit format, issue linking keywords, and template compliance before submission.
issue-to-mr-setup
Create an automation that implements GitLab issues when a configurable trigger label is applied. Polls one or more projects deterministically, clones the default branch, starts one OpenHands conversation per label event, then commits, pushes, and opens the merge request itself.
ship
Deploy feature through automated staging validation to production with rollback testing.
run-plan
Execute implementation plan phases for a change.
deploy
Run the complete ClawBridge release process. This is the ONLY way to deploy — follow every step.