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/kangarooking/loop-engineering-skill/loop-worthiness-testnpx skills add kangarooking/loop-engineering-skill --skill loop-worthiness-testgit clone --depth 1 https://github.com/kangarooking/loop-engineering-skillWhat 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 | $0.00107 | $0.01558 |
| Opus 5 | $0.00053 | $0.00779 |
| Sonnet 5 | $0.00021 | $0.00312 |
| Haiku 4.5 | $0.00011 | $0.00156 |
Grade A, and why
loop-worthiness-test 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Source Metadata
Original cangjie-skill frontmatter from the distillation run:
name: loop-worthiness-test
description: |
判断一个任务是否值得做成 Loop 的四条决策标准。
当用户在纠结"这件事要不要自动化"、"该不该用 loop"、或"为什么我的 loop 得不偿失"时使用。
不适用于: 已经决定要做 loop 后的设计阶段、或一次性任务。
关键 trigger: "这件事值得做 loop 吗"、"该不该自动化"、"loop 成本太高怎么办"。
source_book: "Loop Engineering 视频合集"
source_chapter: 视频3 (小木头引用 Iddo Money) / 视频4
tags: [decision-framework, cost-benefit, automation, checklist]
related_skills: [loop-three-elements, loop-build-path, comprehension-gap]
Loop 适用性四条件测试 — 防止过度工程化
R — Reading (原文)
"他给了4条测试条件,4条都满足做loop才划算。第一是这个活每周以上都会重复... 第二验证能够自动化... 第三你的token预算得扛得住... 第四agent手里有资深工程师那套工具。" — 小木头 (视频3)
"The majority of tasks don't need loops." — Adam Gillock (视频1)
I — Interpretation (自述)
判断一个任务是否值得搭建循环系统,需要同时满足四个条件:
- 高频重复: 任务至少每周做一次。一次性或低频任务不值得搭建 loop 系统。
- 可自动验证: 有测试/Lint/检查能自动拦截坏结果,无需人工审验每条输出。
- Token 预算充足: 能承受反复读取上下文和试错的成本,包括浪费的 token。
- 完整工具链: Agent 拥有日志、运行环境、自测能力,能自己跑代码看结果。
四条都满足才值得做 loop。 这是一个反直觉的过滤器 — 大多数人看到 loop 很酷就想用,不会先做适用性判断。
A1 — Past Application (书中案例)
案例1: 值得做 Loop — 选题收件箱 (视频3)
- 高频: 每天 ✅ | 可验证: 有 topic-score 评级 ✅ | 预算: 小 ✅ | 工具: 有 research API ✅
- 结论: 值得
案例2: 不值得做 Loop — 一次性脚本 (视频1 隐含)
- 高频: 一次性 ❌ | 可验证: N/A | 预算: N/A | 工具: N/A
- 结论: 不值得,单次提示即可
案例3: 部分满足 — 缩略图生成 (视频1)
- 高频: 每周 ✅ | 可验证: 主观评分 ❌ | 预算: 中 ✅ | 工具: 有 ✅
- 结论: 验证环节是瓶颈,需要引入独立评分 agent
A2 — Future Trigger (未来触发)
- 纠结是否自动化时: "我想让 AI 每天做 X,值得做 loop 吗?"
- Loop 成本过高时: "这个 loop 跑一次花太多 token" → 检查条件3和4
- Loop 产出质量差时: "loop 出来的东西不能用" → 检查条件2 (验证是否可靠)
- 团队推广 Loop 时: 用这个测试作为"要不要做"的决策门槛
语言信号: "值得做 loop 吗"、"该不该自动化"、"loop 成本太高"、"这个任务适合 loop 吗"
与相邻 skill 的区别:
loop-three-elements: 假设已决定要做,关注"怎么设计" (本 skill 是前置决策)loop-build-path: 关注构建步骤 (本 skill 是构建前的判断)comprehension-gap: 关注 loop 运行后的风险 (本 skill 是运行前的判断)
E — Execution (可执行步骤)
Step 1: 四条件检查清单
对目标任务逐条检查:
□ 高频重复: 至少每周做一次?
□ 可自动验证: 有客观标准判断好坏?
□ Token 预算: 能承受反复试错?
□ 完整工具链: agent 有日志+环境+自测能力?
What ships with it
2 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.
- 2d ago First seen · 114 lines · 107 tokens per session scan A 3f681be9cc30
loop-worthiness-test is a skill published in the GitHub repository kangarooking/loop-engineering-skill (23 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 1,558 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
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…