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 agentmods add commands/xcodethink/open-claude-code-skills/loopsgit clone --depth 1 https://github.com/xcodethink/open-claude-code-skillsWhat 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 | $0.00031 | $0.00738 |
| Opus 5 | $0.00015 | $0.00369 |
| Sonnet 5 | $0.00006 | $0.00148 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
loops 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 2d 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.
What it actually says
loops — 重复任务配方库（用户触发，零常驻成本）
用户输入 /loops $ARGUMENTS 时，按需加载配方库帮挑配方、填真实命令、过护栏。
立刻读取并完整加载：
~/.claude/loops/COVERAGE.md（覆盖地图：状态+缺口）~/.claude/loops/catalog.md（标准配方 A/B/C/D 四类）~/.claude/loops/my-loops.md（我的实例）- 决策理论如需细则 →
~/.claude/skills/21-任务执行纪律/循环工程-loop.md
执行
无参数 → 直接呈现 COVERAGE 覆盖地图（重点是"当前缺口"段），问用户要补哪个 / 跑哪个。
有参数（一个重复任务） → 按顺序：
- 过决策表四判据：终态能否一条命令判真假？"够好"客观还是主观？频率≥每周？——判 A（可 /goal）/ B（定时）/ C（别 loop）。
- 命中配方 → 从 catalog 取对应配方，把
<...>换成用户项目的真实命令（要问就问，别猜命令）。 - 写停止条件：必须可观测（退出码/文件状态/计数），配
stop after N兜底；不能是意图。 - 过护栏：proactive/
/schedule上云前，逐条过进程爆炸铁律（嵌进程预算，fan-out≥4 先问）+ 云资源铁律 + 本地开发别推部署 → 先征用户同意再起。 - 产出可粘贴命令（
/goal ...//loop .../ cron），但不替用户执行——由用户敲，或明确让我跑才跑。 - 判为 C（别 loop）→ 直说别自动化，给"该怎么做"（
/grill+HITL 等），不硬凑成 loop。
新任务无对应配方 → 先给 catalog 加一条标准配方，再实例化到 my-loops，再给命令。
用户要求加/改/补库（"把 XX 也做成配方"/"改状态"/"加一类"）→ ① 按 catalog 格式加配方 → ② 更新 COVERAGE 状态/缺口 + 最后更新日期 → ③ 需要时更新 my-loops。这是共建路径，见 COVERAGE「共建这个库」。
核心契约：库是菜谱、/goal 是开火——本命令只帮你选菜谱+配好料，不自动下厨；主观/低频/判断型的活明确劝退，不被"只写 loop"带偏。
参数: $ARGUMENTS
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.
- 2d ago First seen · 35 lines · 31 tokens per session scan A d06dc6eb0ea3
loops is a command published in the GitHub repository xcodethink/open-claude-code-skills (2 stars, last pushed 27d ago), licensed MIT. It adds 31 tokens to every session and 738 once invoked, about $0.0002 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 commands, from other repositories
setup-pm
Configure package manager preference.
nopua-en
Manually activate NoPUA clarity mode when stuck — identify the failure pattern and work through stop → observe → transform → act → transcend, driven by wisdom rather than fear.
park
Park current session for later resume (append to Markdown file).
memstack-headroom
Check TokenStack proxy status.
daily
Daily update check — official Anthropic docs diff + guide/CC releases digest.
atomic-help
Route a lost user to the right atomic verb, skill, agent, or binary subcommand. Bare invocation reads git state and recommends one next step. Topic keyword or freeform intent → focused pointer. tour → guided walkthrough of the system. Help router, not duplicated docs.