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/first-principlesnpx skills add coolTheWorld/evolution-skills --skill first-principlesgit 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/first-principles)<a href="https://agentmods.dev/skills/cooltheworld/evolution-skills/first-principles"><img src="https://agentmods.dev/badge/skills/cooltheworld/evolution-skills/first-principles.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 | $0.00027 | $0.00893 |
| Opus 5 | $0.00014 | $0.00447 |
| Sonnet 5 | $0.00005 | $0.00179 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
first-principles 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A problem that keeps needing patches is being solved on the terms of its first solution: path dependence, where every fix inherits the assumptions of the one before. Take the problem back to bedrock — what is confirmed, what is merely accepted, what is actually wanted, what is actually available — and rebuild the path from first principles rather than from what the field does.
Write in the language the user writes in.
1. Pin the problem and the current solution
State the problem the user wants solved and the solution currently in place or currently proposed — the process, the architecture, the system as it runs today, patches included. Where none exists yet, the current solution is whatever the user would build by default. Where it lives somewhere you can read — the codebase, a process document, a config — read it rather than reconstruct it from the user's summary.
If no problem was given, ask one question for it and stop; anything else you need, infer or look up.
Done when the problem and the current solution are each stated in a form the user would sign, and the current solution's patches are listed by name.
2. Decompose to bedrock
Take the problem apart until nothing underneath it can be taken apart further, and show the user what you find, sorted into exactly four bins:
- Basic facts — confirmed and impossible to route around: physics, law, signed contracts, measured numbers, what users have actually done.
- Unverified assumptions — accepted by habit and never tested: "this has to be synchronous", "customers expect a form", "that team cannot own it". The current solution rests on these.
- The real goal — the outcome wanted. The stated ask usually names a means; the goal is what the means was for.
- Resources and constraints — what actually exists: people, money, time, hard deadlines, commitments already made.
The lazy run files everything as fact. The test for a fact is that someone could show it to you; anything believed because it has always been true, or because a vendor said so, goes into assumptions with a note of what would verify it. The test for a constraint is that violating it costs something real; a preference dressed as a constraint goes into assumptions too.
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 · 52 lines · 27 tokens per session scan A b3f9aac530d9
first-principles is a skill published in the GitHub repository coolTheWorld/evolution-skills (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 27 tokens to every session and 893 once invoked, about $0.0001 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.