Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tranfu-labs/tranfu-skillsnpx agentmods add commands/tranfu-labs/tranfu-skills/conventionsWrote 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/conventions)<a href="https://agentmods.dev/commands/tranfu-labs/tranfu-skills/conventions"><img src="https://agentmods.dev/badge/commands/tranfu-labs/tranfu-skills/conventions/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/conventions"><img src="https://agentmods.dev/badge/commands/tranfu-labs/tranfu-skills/conventions.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 | $0.01389 |
| Opus 5 | $0.00000 | $0.00694 |
| Sonnet 5 | $0.00000 | $0.00278 |
| Haiku 4.5 | $0.00000 | $0.00139 |
Grade A, and why
conventions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ ad-hoc 速查: 本文件是 CLI ad-hoc 速查(排障 / 临时操作用),reconcile flow 主链路不依赖;命令需要时手动跑。reconcile 主链路全走 HTTP API,见 ../scenarios/reconcile-deployment.md 和 ../references/coolify-api-fields.md。
通用约定
这一份是所有场景共用的横切约定。跑任何场景前先把这里读懂,再去看 prerequisites.md 和具体的
scenarios/<name>.md,可以避免大量重复说明。
全局 flag
每条 coolify 命令都可以带这些通用 flag:
--context <name>:临时切实例,单次有效,不会改 default context。多实例环境里慎用 default, 涉及到生产 / 测试切换时 MUST 显式带--context=<name>,NEVER 先coolify context use改 default 再跑命令。--token <token>:用一个外部 token 跑这条命令,覆盖当前 context 里存的 token。--format <fmt>:输出格式,可选table(默认) /json/pretty。--show-sensitive或-s:显示被默认遮蔽的敏感字段(token、密码、IP、邮箱等)。--debug:打开 CLI 调试日志。出现疑似 CLI 自身行为不对时再开。
输出格式与解析
本 skill 的所有场景统一用 --format json + jq 来解析输出,目的:
- 用脚本可读的方式断言"列表是否为空 / 长度是否为 1 / 是否存在某个 name",而不是肉眼看 table。
- 错误处理统一。
jq -e在结果为空或 false 时退出码非零,可以直接当作 if 条件用。
几个本 skill 反复用到的 jq 模式:
# 通过 name 找 UUID(例:找名为 foo-app 的 project)
coolify project list --format json \
| jq -r '.[] | select(.name == "foo-app") | .uuid'
# 断言数组长度(例:要求恰好一个 GitHub App)
COUNT=$(coolify github list --format json | jq 'length')
[ "$COUNT" -eq 1 ] || echo "数量不是 1(实际 $COUNT),终止"
# 断言某条记录存在(jq -e 在空结果时退出码非零)
coolify github repos <github-app-uuid> --format json \
| jq -e '.[] | select(.full_name == "tranfu-labs/foo-app")' > /dev/null \
|| echo "未找到该仓库,终止"
如果用户机器没有 jq,先让其安装:
- macOS:
brew install jq - Linux:
apt install jq或yum install jq
UUID 与 ID 的区别
Coolify 的资源标识规则只有一条例外:
- 几乎所有资源都用 UUID:app / project / server / database / service / private-key / github-app / deployment 等。
- 唯一例外是 teams:
coolify teams get <team_id>用的是数字 ID,不是 UUID。
涉及 teams 时不要把 UUID 当成 ID 来传。其它资源放心当 UUID 处理。
别名
CLI 命令树里大多数主名词都有别名,便于打字。这些别名是同一个命令的不同写法,文档里用主名词:
| 主名词 | 别名 |
|---|---|
app |
apps / application / applications |
database |
databases / db / dbs |
service |
services / svc |
github |
gh / github-app / github-apps |
private-key |
private-keys / key / keys |
project |
projects |
server |
servers |
resource |
resources |
team |
teams |
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.
- 8d ago First seen · 103 lines · 0 tokens per session scan A cda3773afb9f
conventions 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 1,389 tokens. 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 2026-09-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.