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/micheltlutz/dev-challenge/challenge-workflownpx skills add micheltlutz/dev-challenge --skill challenge-workflowgit clone --depth 1 https://github.com/micheltlutz/dev-challengeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/micheltlutz/dev-challenge/challenge-workflow)<a href="https://agentmods.dev/skills/micheltlutz/dev-challenge/challenge-workflow"><img src="https://agentmods.dev/badge/skills/micheltlutz/dev-challenge/challenge-workflow.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00087 | $0.01276 |
| Opus 5 | $0.00044 | $0.00638 |
| Sonnet 5 | $0.00017 | $0.00255 |
| Haiku 4.5 | $0.00009 | $0.00128 |
Grade A, and why
challenge-workflow 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 4d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Challenge workflow
The spec-driven loop this lab is built around. Follow it yourself, and walk the learner through it.
Before anything: posture
Read "First: which job are you doing?" in AGENTS.md.
Default to mentoring. The person is here to learn; the code is the medium, not the deliverable. Plan with them, review what they write, name the failing criterion and explain why — but do not hand over the implementation unless they ask for it.
They can switch you off this at any time: "just write it", "show me a
solution", --solve. When they do, switch cleanly, say you have switched, and
do a proper job. Withholding while pretending you cannot help is worse than
useless.
Scaffolding, config, build setup and boilerplate are always fine to write
outright. Nobody learns from a tsconfig.json. Save the mentoring for the
logic the challenge is actually about.
1. Read the spec
cat specs/challenges/<id>/spec.md
cat specs/challenges/<id>/acceptance.md
Never answer from readme_files/ — those are redirect stubs — or from how such
an API usually works. The briefs disagreed with the running API for a long time;
that is why this layer exists.
If it is a web or mobile challenge, also read:
specs/design/style-guide.mdspecs/design/tokens.css— import it, do not hard-code hex- the
mockups:listed in the frontmatter
Note the testids: list. It is a contract: the harness drives the UI through
those values, so an implementation that omits them cannot be verified no matter
how good it looks.
2. Clarify
Ambiguity in a spec is a bug in the spec, not something to guess past. Surface it, state the assumption you would make, and suggest opening an issue. Fixing a spec is a real contribution and the specs say so.
3. Plan
Turn the acceptance criteria into a checklist before writing code. Order it so that the criteria a failure would cascade from come first — usually authentication, then scoping, then the feature.
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.
- 4d ago First seen · 134 lines · 87 tokens per session scan A 44f5c3de6da9
challenge-workflow is a skill published in the GitHub repository micheltlutz/dev-challenge (32 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 1,276 once invoked, about $0.0004 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
phone-ui-demos
把产品/知识点/文案做成"手机系统 UI 风格"的电影化网页演示动画——观众像在看一台真手机的精心编排录屏：锁屏通知、聊天、设置页、控制中心、App 界面逐镜头呈现，HyperOS/MIUI 级手感动效 + 虚拟时钟播放器，可全屏录屏当成片。只要用户提到：手机 UI 演示、手机录屏风格动画、App 演示网页、把产品做成手机里的演示、锁屏通知动画、系统 UI 风格演示页、或要求改造升级一批手机风格演示页——就用本 Skill。内容完全开放不设限：任何产品功能、课程知识、科普叙事都能转译成"手机里发生的事"。.
animation-vocabulary
Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and…
fluencyloop
FluencyLoop — stay fluent in code as AI writes it. Router/overview for the per-feature loop (design → build+teach → review), the optional up-front planning stage for large chunks, the woven-in constitution that grows from decisions, plus post-merge backfill. Use when the user mentions FluencyLoop, "fluency", the…
qa-mobile-testing
当需要测试 iOS/Android 原生 App、H5 页面或小程序的移动端专项场景时使用此技能。移动端的坑主要不在功能逻辑上——中断（电话/通知/低电量）、弱网/断网/网络切换、前后台切换、系统权限管理、多机型适配和各种系统版本兼容才是重灾区。不要只测功能流程，移动端的 Bug 有一半以上是中断和兼容性相关的。输出按中断/网络/权限/兼容/性能分类的测试要点清单。.
expo-app-design
Build beautiful cross-platform mobile apps with Expo Router, NativeWind, and React Native.
expo-deployment
Deploy Expo apps to iOS App Store, Android Play Store, and web.