Agent skill

Loop Design Check

by qshanx in qshanx/docs-governance

把一个任务"写成"一个目标导向的 loop,并"检查"这个 loop 写得对不对、会不会跑飞——防止空转烧钱 / Goodhart 作弊 / 把错的干到底。两个动作:① 写 loop(先做减法判该不该建 → 定可判定目标 → 选回路类型 → 选骨架)② 体检 loop(过五个崩法 + 可判定性 + 边界 + 降级 + judge 独立 + 判断留人红线)。中文触发:写 loop、设计…

MITAuto-check passedAgent Workflows

Install Loop Design Check

skills CLI
$ npx skills add qshanx/docs-governance --skill loop-design-check -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install qshanx/docs-governance loop-design-check --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/qshanx/docs-governance.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/loop-design-check .claude/skills/loop-design-check && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
loop-design-check
GitHub stars
132
Token cost
~1.2k tokens
SKILL.md length
362 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

把一个任务"写成"一个目标导向的 loop,并"检查"这个 loop 写得对不对、会不会跑飞——防止空转烧钱 / Goodhart 作弊 / 把错的干到底。两个动作:① 写 loop(先做减法判该不该建 → 定可判定目标 → 选回路类型 → 选骨架)② 体检 loop(过五个崩法 + 可判定性 + 边界 + 降级 + judge 独立 + 判断留人红线)。中文触发:写 loop、设计…

  • Works in 5 steps: 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 =… → 有失败降级方案——重试上限 N + 超了升级人工。 → …
  • Tasks that involve Autonomous loops
  • SKILL.md covers 何时用 / 不用, 红线前提:两层反馈(先记死,违反则全盘皆输), 动作一:写一个 loop(5 步) and 动作二:检查一个 loop 对不对(体检清单 = 五个崩法防呆), plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Loop Design Check is an agent skill from qshanx/docs-governance. 把一个任务"写成"一个目标导向的 loop,并"检查"这个 loop 写得对不对、会不会跑飞——防止空转烧钱 / Goodhart 作弊 / 把错的干到底。两个动作:① 写 loop(先做减法判该不该建 → 定可判定目标 → 选回路类型 → 选骨架)② 体检 loop(过五个崩法 + 可判定性 + 边界 + 降级 + judge 独立 + 判断留人红线)。中文触发:写 loop、设计 loop、做一个 loop、把任务变 loop、agent 自动循环、检查 loop 对不对、loop 体检、loop 会不会跑飞、loop 空转烧钱、loop 作弊、目标导向循环、可判定目标、五个崩法、plan build judge、文档驱动派活、该不该建 loop。English triggers: design an agent loop, write a loop, check a loop, loop review, prevent runaway loop, goal-oriented loop, decidable goal, plan build judge.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Autonomous loops. The repository describes itself as: Claude Code、Codex 与 ChatGPT 的文档驱动开发治理插件:防文档腐烂、维护上下文与决策、契约协作、测试与回归证据。 The licence is MIT.

When your agent uses it

  • Tasks that involve Autonomous loops

Example prompts

  • “一个目标导向的 loop,并”
  • “/loop-design-check”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 完成标准可被机器验证。
  2. 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。
  3. 有失败降级方案——重试上限 N + 超了升级人工。
  4. 目标分层。
  5. 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。

What it can do on your machine

Read from SKILL.md and the folder at commit 520696e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Loop Design Check loads about 1.2k tokens when it runs. Until then it costs about 126 tokens; SKILL.md has 362 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~126
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from qshanx/docs-governance at commit 520696e, republished under its MIT licence (© qshanx). 362 words, ~1,191 tokens.

Download SKILL.mdSave it as .claude/skills/loop-design-check/SKILL.md (or your agent's skills folder).
name
loop-design-check
description
把一个任务"写成"一个目标导向的 loop,并"检查"这个 loop 写得对不对、会不会跑飞——防止空转烧钱 / Goodhart 作弊 / 把错的干到底。两个动作:① 写 loop(先做减法判该不该建 → 定可判定目标 → 选回路类型 → 选骨架)② 体检 loop(过五个崩法 + 可判定性 + 边界 + 降级 + judge 独立 + 判断留人红线)。中文触发:写 loop、设计 loop、做一个 loop、把任务变 loop、agent 自动循环、检查 loop 对不对、loop 体检、loop 会不会跑飞、loop 空转烧钱、loop 作弊、目标导向循环、可判定目标、五个崩法、plan build judge、文档驱动派活、该不该建 loop。English triggers: design an agent loop, write a loop, check a loop, loop review, prevent runaway loop, goal-oriented loop, decidable goal, plan build judge.
metadata.origin
小磊 · 控制论×Loop×Goal

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:

  1. 完成标准可被机器验证。
  2. 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。
  3. 有失败降级方案——重试上限 N + 超了升级人工。
  4. 目标分层。
  5. 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 /schedulecron 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。)

步 3 · 选骨架

守成型(看护已有东西)→ 文档驱动派活 loop 不是"定时跑固定检查",是 "定时读文档、文档变了才派活"。文档 = 任务队列 + 状态机 + 人机接口。 三条纪律:① 问题列只人写、结果列只 loop 写、状态单向推进不回头 ② 退出码是终审(脚本 exit 1 就以脚本为准)③ 状态推到"待验证"为止,"已完成"那格只有人能扳——loop 当工人,不当验收官。

产出型(从零搭东西)→ plan / build / judge 三角色循环

角色干啥关键
Plan把目标拆成 spec + 可判定的验收条件验收条件必须能被脚本判
Build照 spec 写不准改验收条件
Judge独立跑验收,过→停 / 不过→带失败原因回 Build独立 + 确定性规则

三条铁律(全押在 judge):① Judge 必须独立——不能是 Build 那个 agent(自己批作业必放水)② 用确定性规则——pytest / 对账差异 / 类型检查 / diff,不靠"看着对" ③ 不准 Build 改验收条件过关。重试 3 次还不过 → 升级人工。

Show full SKILL.md (124 more words)Show less
步 4 · 加阻尼(防震颤 / 跑飞)

重试上限、硬停、人扳最后一格 = 阻尼。没有阻尼的负反馈会震颤(Ralph Wiggum loop:在原地空转烧钱)。

步 5 · 落地三档(别一上来就全自动)

① 先手动跑通一次(逼自己讲清"judge 到底怎么判")→ ② 固化成 skill / Claude Code sub-agents(主 Claude 循环派 plan/build/judge)→ ③ 挂 cron / hermes 全自动。


动作二:检查一个 loop 对不对(体检清单 = 五个崩法防呆)

拿写好的 loop 逐条过。命中任一条 = 这 loop 会出事,打回重写。 这五条是负面经验(gotchas),比正面规则值钱。

#崩法(会怎么坏)体检问题(命中即红)抗体
1目标是句正确的废话 → 空转烧钱退出条件能被机器判 yes/no 吗?还是"管好 / 做好"这种?换成可判定的结果条件(动作一·步1)
2验证写成"检查对不对" → agent 自信说没问题就停judge 是不是被告自己?验证靠"看着对"还是确定性规则?对账 + 退出码说了算 + judge 独立
3(最痛)只卡"测试全过" → agent 删了测试有没有边界条件("不能怎么做")?还是只有完成标准?完成标准 + 边界 一起定(Goodhart 抗体)
4指望 agent 中途来确认 → 它不会,把错的干到底有没有"运行中才需要人澄清"的点?所有澄清前置,出发前一次答死
5CLAUDE.md 膨胀 + 记忆过期 → loop 越快错越多它依赖的文档 / 记忆新鲜吗?谁维护?记忆三层 + 定期 lint 体检

再加判 3 条红线(违反任一 = 不准上自动):

  • 判断留人:验收 / "已完成"那格人来扳,loop 不当验收官。
  • 责任不可转移:凡"失败后果你担不起"的事(合错 PR / 发错图 / 分错钱),不自动交权。
  • 反直觉警告:越是"自改进 / 自己改规则"的 loop,越需要更严的人审(看它把规则改成了啥),不是更放手。机器快到来不及拦,人的判断必须卡在动手之前(硬 gate),不能出错了再补。

一句话收口

写 loop 真正吃劲的不是"会不会写循环",是"定一个机器能对账的目标"——可判定、带边界、对账型。控制器要确定性且外置;判断和标准留人;系统会熵增所以要持续维护。 循环只奖励已经想明白的人。指望它替你想,它会很乐意带着你一起想错。


来源:小磊《控制论×Loop×Goal——把 LLM 管成目标导向系统》(vault 01-AI实践经验/10)。plan/build/judge 源 Anatoli《Loops explained》/ Addy《Loop Engineering》;两层反馈 + 红线源 维纳《人有人的用处》(1950)。 机制层(怎么搭循环架构)见 autonomous-loops / continuous-agent-loop;本 skill 不重写机制,只管目标与防跑飞。

© qshanx, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/loop-design-check of qshanx/docs-governance.

Open the folder on GitHubat commit 520696e

Compare with similar skills

Loop Design Check next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Loop Design Check compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Loop Design Check this skillqshanx/docs-governance132—~1.2kAutomated safety check: PassMIT
Show Me Your Work Decision Logcursor/plugins10k9 repos~1.6kAutomated safety check: PassNone
Autoresearch Iteration Loopuditgoenka/autoresearch6.5k1 repos~2kAutomated safety check: PassMIT
PUA Looptanweai/pua20k1 repos~1.1kAutomated safety check: PassMIT
AutopilotYeachan-Heo/oh-my-claudecode40k1 repos~4.4kAutomated safety check: PassMIT
Install Loop Engineeringcobusgreyling/loop-engineering11k1 repos~648Automated safety check: PassMIT

Similar skills

  • Official

    Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.

    10k GitHub starsUsed in 9 repos~1.6k tokens
    Agent WorkflowsAuto-check passed
  • Autoresearch Iteration Loop

    uditgoenka/autoresearch

    Runs an autonomous modify, verify, keep-or-discard loop against any metric, with subcommands for planning, debugging, fixing, security audits, shipping and more.

    6.5k GitHub starsUsed in 1 repo~2k tokens
    Agent WorkflowsAuto-check passed
  • PUA Loop

    tanweai/pua

    Runs an unattended iterate-until-verified loop in which a user-set verify command, not the agent's own claim, decides when the task is finished.

    20k GitHub starsUsed in 1 repo~1.1k tokens
    Agent WorkflowsAuto-check passed
  • Autopilot

    Yeachan-Heo/oh-my-claudecode

    Takes a short product idea through requirements, design, planning, parallel implementation, QA cycles and multi-reviewer validation to produce working code.

    40k GitHub starsUsed in 1 repo~4.4k tokens
    Agent WorkflowsAuto-check passed
  • Install Loop Engineering

    cobusgreyling/loop-engineering

    Installs Loop Engineering into a project through the single @cobusgreyling/loop CLI, scaffolding a report-only loop and a readiness score.

    11k GitHub starsUsed in 1 repo~648 tokens
    Agent WorkflowsAuto-check passed
  • Loopy

    Forward-Future/loopy

    Discover, find, compare, audit, repair, adapt, craft, run, debrief, save, and prepare repeatable AI-agent loops for publication.

    3.2k GitHub stars~3.9k tokensUpdated 27 days ago
    Agent WorkflowsAuto-check passed

More from qshanx/docs-governance

All 10 skills in this repo
  • Agent Entrypoints

    qshanx/docs-governance

    根据项目事实与已确认讨论生成、精简或审查 AGENTS.md / CLAUDE.md,明确共享规则主文件、可执行约束、PRD / Spec 读取路标和验证入口。用于项目入口只有空模板、规范含糊、双入口冲突或需要设置 Agent 项目说明时。English triggers: AGENTS.md, CLAUDE.md, project instructions, agent entrypoint…

    132 GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check passed
  • Module Regression

    qshanx/docs-governance

    大项目模块间联动回归——一份 REGRESSION.md 回归台账登记"每个模块的下游消费者 + 可执行的回归验收命令",每次改动后照台账跑回归审计,防"改一个模块悄悄弄坏其他模块"。判决靠退出码,不靠 AI 看着没问题。中文触发:模块回归、回归台账、回归审计、改A坏B、模块联动检查、影响面检查、模块牵连、下游验证、大项目改动检查。English triggers: module…

    132 GitHub stars~811 tokensUpdated 3 days ago
    Auto-check passed
  • Contract First

    qshanx/docs-governance

    分前端/后端(或多个服务)多端开发的项目,用 CONTRACT.md 指向的唯一机器契约,各端只照它各做各的,防止字段漂移导致集成时白屏。支持单会话多 agent 和多终端各自跑两种模式。只要项目有前后端/多服务、接口字段老对不上、各端联调卡住、某端改了字段忘了通知别人、或前端为渲染一个页面要调一堆接口拼数据,就用这个…

    132 GitHub stars~1.2k tokensUpdated 3 days ago
    Auto-check passed
  • Docs Governance

    qshanx/docs-governance

    作为面向长期 AI 协作项目的知识、决策与验证治理总入口,把优秀 Agent 的一次性工作沉淀为可继承、可验证、可持续演进的项目集体能力;根据用户意图把任务路由到活文档、领域上下文与 ADR、变更影响、接口契约、测试资产、模块回归或闭环设计能力,并在大型变更中组织正确顺序。用于用户只说“文档治理”“项目治理”“帮我整理项目知识”“改完怎么收尾”而未指定具体…

    132 GitHub stars~485 tokensUpdated 3 days ago
    Auto-check passed
  • Living Docs Governance

    qshanx/docs-governance

    把长期项目的文档当成一个小系统来维护,防止文档腐烂——四份各司其职的脊柱文件(CLAUDE.md 共享章程 / CLAUDEMAP.md 地图 / PROJECTSTATUS.md 健康仪表盘 / PROJECTLOG.md 流水账)+ Codex 的 AGENTS.md 入口桥接 + 固定读序,并按需连接 ARCHITECTURE、CONTEXT、ADR、契约、测试、回归和 Issue…

    132 GitHub stars~4.1k tokensUpdated 3 days ago
    Auto-check passed
  • Product Evolution

    qshanx/docs-governance

    在 docs 下建立或维护产品管理入口,登记材料来源,统一需求编号、状态与修订,连接需求池、单需求、版本及验收复盘,并只读审查需求演变是否可追溯。用于产品文档管理员、PRD 版本混乱、产品进展难以理解、已确认决定未回写或需要产品文档审查时。English triggers: product documentation manager, product evolution, PRD…

    132 GitHub stars~2.1k tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Loop Design Check

What does Loop Design Check do?

把一个任务"写成"一个目标导向的 loop,并"检查"这个 loop 写得对不对、会不会跑飞——防止空转烧钱 / Goodhart 作弊 / 把错的干到底。两个动作:① 写 loop(先做减法判该不该建 → 定可判定目标 → 选回路类型 → 选骨架)② 体检 loop(过五个崩法 + 可判定性 + 边界 + 降级 + judge 独立 + 判断留人红线)。中文触发:写 loop、设计…. Loop Design Check is an agent skill from qshanx/docs-governance. 把一个任务"写成"一个目标导向的 loop,并"检查"这个 loop 写得对不对、会不会跑飞——防止空转烧钱 / Goodhart 作弊 / 把错的干到底。两个动作:① 写 loop(先做减法判该不该建 → 定可判定目标 → 选回路类型 → 选骨架)② 体检 loop(过五个崩法 + 可判定性 + 边界 + 降级 + judge 独立 + 判断留人红线)。中文触发:写 loop、设计 loop、做一个 loop、把任务变 loop、agent 自动循环、检查 loop 对不对、loop 体检、loop 会不会跑飞、loop 空转烧钱、loop 作弊、目标导向循环、可判定目标、五个崩法、plan build judge、文档驱动派活、该不该建 loop。English triggers: design an agent loop, write a loop, check a loop, loop review, prevent runaway loop, goal-oriented loop, decidable goal, plan build judge.

When should I use Loop Design Check?

Loop Design Check fits situations like: tasks that involve Autonomous loops.

How do I install Loop Design Check in Claude Code?

Run `npx skills add qshanx/docs-governance --skill loop-design-check -a claude-code`. Or copy the skill folder (skills/loop-design-check in qshanx/docs-governance) into .claude/skills/loop-design-check in your project. Claude Code loads it when a task matches its description.

How do I install Loop Design Check in Codex?

Run `npx skills add qshanx/docs-governance --skill loop-design-check -a codex`. Or copy the skill folder (skills/loop-design-check in qshanx/docs-governance) into .agents/skills/loop-design-check in your project. Codex loads it when a task matches its description.

Can I use Loop Design Check in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add qshanx/docs-governance --skill loop-design-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/loop-design-check, .gemini/skills/loop-design-check, .github/skills/loop-design-check and .opencode/skills/loop-design-check in your project.

What does Loop Design Check need to run?

SKILL.md names no scripts, command-line tools or credentials: Loop Design Check is instructions for the agent only.

Does Loop Design Check access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Loop Design Check safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Loop Design Check use?

Loop Design Check is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Loop Design Check use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Loop Design Check?

Skills that share tags, products or a category with Loop Design Check: Show Me Your Work Decision Log (cursor/plugins, 10k stars), Autoresearch Iteration Loop (uditgoenka/autoresearch, 6.5k stars), PUA Loop (tanweai/pua, 20k stars) and Autopilot (Yeachan-Heo/oh-my-claudecode, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Loop Design Check?

qshanx (a GitHub user) maintains it in qshanx/docs-governance, which has 132 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 5, 2026.

Source: qshanx/docs-governance on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.