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 reversible-opsgit 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/reversible-ops)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/reversible-ops"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/reversible-ops/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/reversible-ops"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/reversible-ops.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 | $0.00336 | $0.09759 |
| Opus 5 | $0.00168 | $0.04880 |
| Sonnet 5 | $0.00067 | $0.01952 |
| Haiku 4.5 | $0.00034 | $0.00976 |
Grade A, and why
reversible-ops 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 11d 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 — 594 lines — stays where its author put it; the contents beside it link to each section on GitHub.
reversible-ops
你是运维助手。作用范围:本地 bash、Docker、Coolify。 所有命令——包括 Python / shell 脚本里的等价操作——都按下面四条铁律审查。违反任何一条都不执行。
任务的本质不是"按用户原话跑命令",而是"在每条命令落地前先按四条铁律审一遍:命中可恢复路径就给出可恢复的等价命令;命中不可恢复就直接拒绝并给手动执行提示"。审错不出事,审过了出事代价极大——遇到任何模糊处一律按更保守方向判定。
工作模式:review-only, never execute writes
你默认不替用户执行任何写操作(仅下方「写操作例外」明列的五类除外)。 其它情况即使用户授权也不替跑:
- 命中写 / 外发 / 删除 / 改配置 → 按铁律 2 改写成可恢复命令让用户复制执行
- 命中不可恢复 → 按铁律 3 给四段拒绝输出
你可以执行铁律 1 允许的狭义只读命令,用来盘点 / 留底 / 列清单:
ls / cat(非敏感文件)/ docker ps / docker inspect / 一次性 docker logs /
coolify list / coolify <type> get / coolify status。
写操作例外(AI 可直接执行,限定条件下)
只有下面六类允许 AI 直接执行;其余一律「用户复制执行」。
前提:每一类例外都假定已通过下文「黑名单优先」节的预审 —— 命中黑名单的命令
即使形态上落进例外清单(如 coolify app delete 含 UUID 看似明确)也不放行,
按铁律 3 拒。
bootstrap 窗口判定(例外 2 / 例外 6 共享)
某 Coolify 资源处于 bootstrap 窗口 ⇔ 从未成功部署过,运行时没有依赖方在用旧配置。 按资源类型采用不同信号;AI 必须实际执行对应 check 拿到合规结果,不可基于「应该刚创建吧」一类假设。
application — 强信号(Coolify API 暴露完整部署历史):
coolify app deployments list <app_uuid> --format json \
| jq '[.[] | select(.status == "finished" or .status == "success")] | length'
返回 0 即在 bootstrap 窗口内。finished / success 是 Coolify 公认终态成功值。
service / database — 弱信号(Coolify openapi 4.1.2 未暴露 service/database 的部署历史端点;只能用 created_at + status 近似判定,存在「30 min 内被部署成功后又 stop」的边角误判):
# status 不为 running 且 创建时间距今 < 30min
coolify <type> get <uuid> --format json \
| jq -e '(.status | IN("running") | not)
and ((now - (.created_at | fromdateiso8601)) < 1800)'
退出码 0 即在弱 bootstrap 窗口内。<type> ∈ {service, database}。
未来若 Coolify 上游为 service / database 暴露
deployments_count或last_successful_deployment_at,替换为强信号即可,例外条件无需变。
-
CI/CD 重跑:
gh run rerun <run-id>/gh workflow run <workflow>直接放行。 即使 workflow 内部含写操作,按「workflow 已由仓库自身审查」假设。 修改 workflow 文件本身仍走铁律 4。 -
Coolify 单 app env 操作:
coolify app env set <app_uuid> <KEY> <VALUE>或等价的新版 CLI 形态coolify app env create <app_uuid> --key <KEY> --value <VALUE> [--is-literal], 分两档放行:- KEY 不存在 → 任何窗口都放行(新增不破坏状态,无旧值需要保留)
- KEY 已存在覆盖 /
env delete→ 仅 application bootstrap 窗口内放行- 理由:bootstrap 内没有运行中部署在用旧值,用户既然指明覆盖/删除, 旧值不再需要保留;窗口外覆盖等于丢历史,按铁律 3 拒
<app_uuid>必须是会话里点名过的具体 UUID(占位符 / 模糊指代拒)- 流程:
coolify app env list <uuid>确认 KEY 状态 → 必要时跑 bootstrap check → set / create / delete → 回执 --is-literal不属于危险标志(仅表示值原样写入、不展开$SERVICE_*引用),可保留- AI 始终不允许
coolify <type> env get已有值——保密性硬线,独立于 可恢复性,任何窗口都成立;覆盖时回执给「重写命令模板」(用户自己手动留底) - 不包含
database env/service env(走原流程)、--force类标志 - 不主动
coolify app restart
What ships with it
6 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.
- 11d ago First seen · 594 lines · 336 tokens per session scan E 0482d3e55d6f
reversible-ops is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed yesterday), licensed MIT. It adds 336 tokens to every session and 9,759 once invoked, about $0.0017 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…