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 coolTheWorld/evolution-skills --skill deconstructgit 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/deconstruct)<a href="https://agentmods.dev/skills/cooltheworld/evolution-skills/deconstruct"><img src="https://agentmods.dev/badge/skills/cooltheworld/evolution-skills/deconstruct/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/cooltheworld/evolution-skills/deconstruct"><img src="https://agentmods.dev/badge/skills/cooltheworld/evolution-skills/deconstruct.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 | $0.00031 | $0.00973 |
| Opus 5.5 | $0.00012 | $0.00389 |
| Sonnet 5.5 | $0.00006 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
deconstruct 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 1mo 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Admiring a finished work teaches nothing; the lessons sit in the choices its maker made and never wrote down. Deconstruct the exemplar to recover those choices, then keep only what is transferable to the user's own work.
Write in the language the user writes in.
1. Take in the exemplar and the goal
The user supplies two things: the exemplar (a product page, webpage, plan, process doc, dashboard, or other finished work) and what they want to learn from it. If either is missing, ask one question for it and stop.
When the exemplar is a URL, fetch it with WebFetch and work from the fetched page; when the fetch returns nothing usable, ask the user to paste the content and stop.
Hold the learning goal as the filter for every later step: the same page deconstructed for "how it sells" and for "how it organises information" yields different rules.
Done when the full exemplar is in hand and the learning goal is stated in one sentence you can test a rule against.
2. Name the problem it solves
Open with one sentence: what problem this work solves, and for whom. Describe the problem from the audience's side ("lets a first-time visitor decide in thirty seconds whether the tool fits"); "a SaaS landing page" names a category, not a problem.
Done when the sentence names the problem and the person who has it, and contains no feature of the artifact.
3. Deconstruct why it works
Reverse-engineer the exemplar through four lenses, each backed by something you can point to in the artifact:
- Who it serves and what its goal is. The specific person in a specific moment, and the single outcome the maker built it to produce. "Users" and "to inform" are placeholders; the real answer says what the maker counts as success.
- What structure or flow it uses. The order of parts and the reason for the order: what each part sets up for the next, where the audience is taken first and why. Listing the sections is inventory, not structure.
- Which key choices create the quality gap. Picture the ordinary version of the same thing and name the few choices this maker made differently. A choice earns the list only if removing it would drop the work back to ordinary; praising everything it does well buries the choices that matter.
- What its completion standard is. What the maker evidently checked before calling it done, inferred from what holds across the whole artifact without exception (every claim has a number, every screen has one action).
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.
- 1mo ago First seen · 59 lines · 31 tokens per session scan A 1ec210afe13c
deconstruct is a skill published in the GitHub repository coolTheWorld/evolution-skills (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 31 tokens to every session and 973 once invoked, about $0.0001 per session on Opus 5.5. 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
A guide for creating or improving an agent skill: a SKILL.md file that gives an AI a repeatable workflow for a specific task. It covers the skill’s name, search keywords, instructions, failure handling, and examples where needed.
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…
video-to-guide
Transforms YouTube videos into full, structured written guides — every detail preserved, no summarizing. Use when the user wants to turn a video into a guide, study notes, learning material, or any written format that captures the full depth of the content. The skill fetches the transcript automatically and produces…