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 skills/seekers2001/docs-governance/loop-design-checknpx skills add Seekers2001/docs-governance --skill loop-design-checkgit clone --depth 1 https://github.com/Seekers2001/docs-governanceWhat 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 | $0.00242 | $0.02937 |
| Opus 5 | $0.00121 | $0.01469 |
| Sonnet 5 | $0.00048 | $0.00587 |
| Haiku 4.5 | $0.00024 | $0.00294 |
Grade A, and why
loop-design-check 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 3d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loop 设计 + 体检
一句话前提：LLM 本身是前馈系统（prompt 进 → token 出，跨轮之间没有内建的"朝目标纠偏"能力）。要它表现得像目标导向系统，得在外面包一条反馈回路（loop）。这个 skill 帮你写对这条回路、并体检它不会跑飞。
何时用 / 不用
用：
- 想把一个重复任务交给 agent 自动反复跑（写完测、测完修、改完验…）。
- 已经写了个 loop，但担心它空转 / 作弊 / 跑飞，要体检。
不用：
- 一次性任务 → 直接做，别套循环。
- 纯定时提醒 / 轮询 → 用
/loop命令即可，不需要"设计"。 - "怎么搭循环的工程架构（管道→DAG、长跑恢复）" → 那是机制层，看
autonomous-loops/continuous-agent-loop。本 skill 只管"目标定得对不对、会不会跑飞"这层判断，不重写机制。
红线前提：两层反馈（先记死，违反则全盘皆输）
| 层 | 谁管 | 干什么 |
|---|---|---|
| 执行层（低层） | 机器 / agent | 测"离字面目标还差多少"，死磕缩到 0。机器很强。 |
| 判断层（高层） | 人 | 判"这目标本身对不对、要不要改、要不要停"。机器跳不出自己的回路质疑目标。 |
空调能反馈"离 26 度差多少"，但你发烧想要 28 度时，它判断不了"26 度对不对"——只会死磕 26。"今天该设几度"永远是人。 把判断 / 验收 / 最后一格交给机器 = 撤掉高层反馈 = 机器照着没人质疑的目标又快又狠地狂奔 → 出错。
动作一：写一个 loop（5 步）
步 0 · 先做减法：该不该建？（四条件入场券，缺一票否决）
① 任务每周以上重复 ② 验证能自动化 ③ token 预算扛得住 ④ agent 有"能真跑起来看结果"的工具
任一不满足 → 别建 loop，手动做或换别的方式。
卡住大多数人的不是"会不会写循环"，是"你那个仓库配不配得上一个循环"。配得上的仓库 = 有对账基线（golden sample / 上游合计）+ 单测 + lint 守护。配不上循环的仓库，循环只会放大错。
步 1 · 定一个"可判定"的目标（最吃劲，loop 成败全在这）
整条回路靠"比较器"那句"达成了吗"。比较器能不能干活，全看你给的退出条件能不能被机器清楚判 yes/no。
- ❌ 模糊（"把这个做好""写高级点"）→ 比较器没法判 → 要么永远不放行（卡死反复重试），要么瞎放行/瞎拦截。
- ✅ 可判定（"96 个单测全绿且出改动清单""模块02字段补全、pytest 全过、没改业务逻辑"）→ 一查就知道，回路干净收敛。
目标定义五条框架：
- 完成标准可被机器验证。
- 边界条件和完成标准一起定义（"不能怎么做"）——防 Goodhart，缺边界 = 给 agent 发作弊许可证。
- 有失败降级方案——重试上限 N + 超了升级人工。
- 目标分层。
- 完成标准优先"对账型"而非"断言型"——锚外部事实（golden sample / 上游合计 / 财务勾稽 / 平台后台数字），其次才是自己写的断言。"测试全过"能被钻（改松断言、注水 mock、吞异常）；"和 VBA 差异 < 0.01"钻不了。
自检：把目标念给一个不懂业务的人，他能不能跑一条命令就判出"到没到"？不能 → 还不够可判定，回来改。
步 2 · 选回路类型
| 你的任务 | 回路（控制论对应） | 怎么停 |
|---|---|---|
| 有明确"完成"判据（写到 done / 一批图处理完 / researcher 出 findings） | servo（/goal 型，闭环伺服） |
到目标就停 |
| 没终点、要持续维持（库存预警 / 报表定时体检） | regulator（/loop 型，恒温器） |
不停，有变化才动作（[SILENT] 死区压噪声） |
| 周期采样、满足条件就停（盯 PR 直到 CI 绿） | 带退出的 regulator | 退出条件满足就停 |
| 要"确保某事按时发生" | 把上面包进 /schedule |
cron 到点触发 |
经验法则：有"完成"判据 → servo；要持续维持没终点 → regulator；要"按时发生" → regulator 包进 schedule。 （
/goal本质就是一个总返回 block 的 Stop 钩子：agent 想停但"不准停"直到达标——是 veto，不是 push。）
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.
- 3d ago First seen · 127 lines · 242 tokens per session scan A 711e70d4d330
loop-design-check is a skill published in the GitHub repository Seekers2001/docs-governance (11 stars, last pushed 20d ago), licensed MIT. It adds 242 tokens to every session and 2,937 once invoked, about $0.0012 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…