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 skills add jonZlotnik/how-to-agent --skill prototype-to-learngit clone --depth 1 https://github.com/jonZlotnik/how-to-agentWrote 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/jonzlotnik/how-to-agent/prototype-to-learn)<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/prototype-to-learn"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/prototype-to-learn/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/prototype-to-learn"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/prototype-to-learn.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00055 | $0.00647 |
| Opus 5 | $0.00028 | $0.00324 |
| Sonnet 5 | $0.00011 | $0.00129 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
prototype-to-learn 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 9d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototype to Learn
A prototype answers one question and then dies. Its only product is the lesson. Treat the code as disposable from the first keystroke — that permission is what makes prototyping fast and honest.
When to use
- You can name a single question the prototype must answer ("does this library handle X?", "how does this UI feel?")
- You're about to make a hard-to-reverse decision and haven't validated the underlying assumption
- A debate is going on that data could end faster than discussion
- The cost of getting it wrong in production dwarfs the cost of a half-day spike
Protocol
- Write the question down in one sentence at the top of the file. If you can't, you're not prototyping — you're drifting.
- Strip everything that doesn't answer it. No auth, no error handling, no styling, no tests, no logging beyond what proves the answer. Cardboard, not steel.
- Set a time box. Half a day to two days. Run the prototype, check whether it actually answers the question, and iterate until it does — or until the box runs out, which is itself a finding.
- Record the answer in prose, not in the code. The code is going to disappear. The lesson belongs in a doc, ticket, or design note.
- Delete the prototype (or move to a
spike/branch you won't merge). If it's irresistible, see the red flags below.
Example
# QUESTION: Does library X stream a 1GB file under 200MB RAM?
# No auth, no UI, no error handling — only what proves the answer.
Distinguish from [[tracer-bullet]]
- Prototype is discarded. Tracer is kept.
- Prototype is allowed to be ugly and broken outside its one question. Tracer must be production-quality on the path it covers.
- If you keep finding excuses to "just productionize this prototype", you needed a tracer bullet from the start.
Red flags (rationalizations to reject)
- "It already works, why throw it away?" — Because it skipped everything you'll need in production. Rewriting is faster than retrofitting.
- "I'll just clean it up." — You'll inherit a hundred decisions made under the "this is disposable" license.
- "We don't have time to prototype." — You have even less time to undo a wrong commitment.
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.
- 9d ago First seen · 49 lines · 55 tokens per session scan A 96e4840deed5
prototype-to-learn is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 647 once invoked, about $0.0003 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…