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/cooltheworld/evolution-skills/min-experimentnpx skills add coolTheWorld/evolution-skills --skill min-experimentgit clone --depth 1 https://github.com/coolTheWorld/evolution-skillsWrote 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/cooltheworld/evolution-skills/min-experiment)<a href="https://agentmods.dev/skills/cooltheworld/evolution-skills/min-experiment"><img src="https://agentmods.dev/badge/skills/cooltheworld/evolution-skills/min-experiment.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 5.1 | $0.00031 | $0.01171 |
| Opus 5 | $0.00015 | $0.00585 |
| Sonnet 5 | $0.00006 | $0.00234 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
min-experiment 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 6d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Some decisions get no clearer on paper; the only information left is reality's feedback. Trade the argument for a test: find the assumption the decision hangs on and design the minimum experiment that could falsify it — cheap, reversible, finished inside the cycle — so the user takes a first step tomorrow instead of a decision today.
Write in the language the user writes in.
1. Pin the decision and the cycle
If the argument names no choice or idea, ask one question for it and stop. Take the cycle from the user; when they give none, it is 7 days.
State the decision in one sentence: the option under consideration and what taking it commits the user to.
Done when the option is stated in one sentence and the cycle is a fixed number of days.
2. Surface the three assumptions
List the three assumptions behind the decision that most need verifying — the load-bearing claims that must hold for the decision to be right, which the user is treating as fact without evidence in hand.
A lazy list holds generic worries (I might not have time). Write each assumption as a claim reality can falsify: customers in segment X will pay Y for this, not there is demand. An assumption that a search, a file, or a quick calculation can settle, settle now (WebSearch/WebFetch, the user's own files): report the answer and take the next assumption in its place.
Done when three assumptions are listed, each a falsifiable claim, each unsettled by anything you could look up, and each able to move the conclusion if false.
3. Pick the decisive one
Select the assumption most likely to change the final conclusion. This is a different question from "most uncertain" or "easiest to test": ask of each, if this turned out false, would the user still take the option? The one where the answer changes most is the one to test.
Done when one assumption is chosen and its weight reads as a conditional: if it holds, do A; if it fails, do B.
4. Design the minimum experiment
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.
- 6d ago First seen · 76 lines · 31 tokens per session scan A 29debf836100
min-experiment is a skill published in the GitHub repository coolTheWorld/evolution-skills (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,171 once invoked, about $0.0002 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
skill-creator
Create or improve Zhin Agent skills (SKILL.md). Use when asked to add a skill, write SKILL.md, document a repeatable agent workflow, or refine skill frontmatter/keywords. Triggers: 创建技能, 写 SKILL, skill-creator, 加 skill.
webman
Expert skill for the webman framework (a long-lived, in-memory PHP framework based on workerman). Covers routing, controllers, middleware, database/Redis, custom processes, timers, coroutines (v2), plugin development, and guarding against memory leaks and cross-request state pollution under the resident process model.…
clawallex-skill
Pay for anything with USDC — virtual cards for any online checkout.
building-edgespark-apps
Build and modify EdgeSpark apps. Use when a project has edgespark.toml, the user mentions EdgeSpark, or work involves the edgespark CLI, server SDK types, storage/auth/database workflows, deployment, or @edgespark/web.
edgespark-frontend-design
Design and redesign EdgeSpark frontends with distinctive, production-grade visual direction instead of generic AI-looking UI. Use when building or polishing landing pages, marketing sites, dashboards, auth flows, portfolios, product surfaces, or reusable frontend sections in EdgeSpark, especially when the task…
iflytek-hyper-tts
Use when user asks to synthesize speech, convert text to audio, or read text aloud. 讯飞超拟人语音合成 - 支持文本转语音、语音合成（发音人/语速/语调/音量/输出格式）。大模型语音合成技能。语音合成, 文字转语音, 超拟人, TTS.