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/two-axis-researchnpx skills add coolTheWorld/evolution-skills --skill two-axis-researchgit 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/two-axis-research)<a href="https://agentmods.dev/skills/cooltheworld/evolution-skills/two-axis-research"><img src="https://agentmods.dev/badge/skills/cooltheworld/evolution-skills/two-axis-research.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 | $0.00036 | $0.01215 |
| Opus 5 | $0.00018 | $0.00607 |
| Sonnet 5 | $0.00007 | $0.00243 |
| Haiku 4.5 | $0.00004 | $0.00121 |
Grade A, and why
two-axis-research 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 5d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A subject is explained by the road it travelled and the company it keeps. Run two axes: the vertical asks how it got here and which early choices hardened into path dependence; the horizontal asks how it stands against its alternatives today. The future is readable only where the axes cross, and every claim rests on a primary source or says that it does not.
Write in the language the user writes in.
1. Fix the subject, the cutoff and the evidence bar
With no subject, or one too vague to research, ask one question for it and stop. Name which kind of thing it is — product, company, person, technology, industry or event — because the kind decides what counts as a comparator later.
The research cutoff is the day of execution: state today's date in the report as the cutoff. Where a deep-research mode is available, use it; otherwise WebSearch to find sources and WebFetch to read each in full.
A primary source — official material, raw data, papers, financial reports, interviews — outranks any secondary account of it; when only a secondary source turns up, follow its citations back to the primary. Beside each important conclusion cite the source and its date, in the same sentence or the line after. Write facts, inferences and opinions as separately labelled claims. When sources conflict, present each version side by side with its source; when no evidence turns up, keep the claim and mark it unverified (暂未核实 in Chinese).
Done when the subject and its kind are named, today's date is fixed as the cutoff, and the search means is chosen.
2. Trace the vertical axis
Establish the context and need the subject was born into, and the key drivers — named people, institutions or forces, with what each pushed and why.
Find the major turning points, successes and failures. A turning point is a fork, not a milestone: record what was chosen, what was declined and what it cost.
Then trace forward: which early choices became today's capabilities, which became path dependence, which became baggage. The same choice is often two of these at once; follow each to a concrete present-day 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.
- 5d ago First seen · 67 lines · 36 tokens per session scan A a30081cddb7d
two-axis-research is a skill published in the GitHub repository coolTheWorld/evolution-skills (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,215 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.