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-build-pathnpx skills add kangarooking/loop-engineering-skill --skill loop-build-pathgit 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 | $0.00103 | $0.01491 |
| Opus 5 | $0.00051 | $0.00745 |
| Sonnet 5 | $0.00021 | $0.00298 |
| Haiku 4.5 | $0.00010 | $0.00149 |
Grade A, and why
loop-build-path 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 — 107 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-build-path
description: |
从"手动做事"到"系统自动做事"的四步渐进构建路径。
当用户已经决定要做 loop、但不知道从何入手时;或团队正在将手工流程自动化时使用。
不适用于: 尚未决定要不要做 loop 的任务、或已经稳定运行的 loop 优化。
关键 trigger: "怎么开始做 loop"、"自动化第一步"、"从手动到自动"。
source_book: "Loop Engineering 视频合集"
source_chapter: 视频4 (Idoos Money) / 视频2 (Boris Cherny)
tags: [build-path, incremental, automation, getting-started]
related_skills: [loop-worthiness-test, loop-three-elements, goal-verification]
渐进式 Loop 构建路径 — 从手动到自动的四步
R — Reading (原文)
"The very first thing... do it manually, right? So, confirm the AI can even do the task at all by hand. Next, everyone is turn it into a skill... Next, everyone is the trigger. Now, it runs on a schedule or an event. It is still not a loop yet. It is just an automation. The loop starts, everyone, when you are adding the verification plus state." — Idoos Money (视频4)
I — Interpretation (自述)
构建循环系统不要一步到位,而是按四个阶段渐进:
- 手动验证: 先手动让 AI 完成任务,确认它能做到。不要在你都没验证过的任务上搭建自动化。
- 封装成 Skill: 把指令固化为 SKILL.md,让每次执行一致。此时是"可重复的手动"。
- 加触发器: 加入定时 (cron) 或事件触发。此时是"自动化",但还不是 loop — 因为没有验证和迭代。
- 加验证 + 状态: 加入自动验证环节和持久化状态记录。此时才成为真正的 Loop。
关键洞察: 自动化 ≠ Loop。自动化是"按时间表执行",Loop 是"执行→验证→调整→再执行"的闭环。
A1 — Past Application (书中案例)
案例1: 选题收件箱 (视频3)
- Step 1: 手动用 research 工具拉取资讯 → 确认可行
- Step 2: 把指令写成 skill (research + topic-score)
- Step 3: 加 cron 触发 (每天早上 8 点)
- Step 4: 加 inbox.md 作为持久化状态 + 评级作为验证
案例2: Boris 的多 Loop 系统 (视频2)
- 先手动跑 support 确认 AI 能处理 → 封装成 skill → 加 30 分钟触发 → 加 signals 文件夹作为状态
A2 — Future Trigger (未来触发)
- 开始做第一个 loop 时: "我想自动化 X,从哪里开始?"
- Loop 搭建失败时: "做了个 loop 但产出很差" → 检查是否跳过了 Step 1
- 团队推广 loop 时: 用这个路径作为"入门指南"
- 从自动化升级到 loop 时: "我的 cron job 已经跑很久了,怎么升级成 loop?"
语言信号: "怎么开始做 loop"、"自动化第一步"、"从手动到自动"、"我的 cron 怎么升级"
与相邻 skill 的区别:
loop-worthiness-test: 判断要不要做 (本 skill 是决定后如何做)loop-three-elements: 静态结构分析 (本 skill 是动态构建过程)goal-verification: 关注验证设计 (本 skill 关注整体路径)
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 · 107 lines · 103 tokens per session scan A 56bac4cd9e09
loop-build-path is a skill published in the GitHub repository kangarooking/loop-engineering-skill (23 stars, last pushed 2mo ago), licensed MIT. It adds 103 tokens to every session and 1,491 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…