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 fact-checkgit 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/fact-check)<a href="https://agentmods.dev/skills/cooltheworld/evolution-skills/fact-check"><img src="https://agentmods.dev/badge/skills/cooltheworld/evolution-skills/fact-check.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 | $0.00033 | $0.01191 |
| Opus 5 | $0.00016 | $0.00596 |
| Sonnet 5 | $0.00007 | $0.00238 |
| Haiku 4.5 | $0.00003 | $0.00119 |
Grade A, and why
fact-check 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 7d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humans and models both hallucinate, and the text in front of you may be either's. Doubt it by default: split the claim into what can be checked and what cannot, trace every fact to its primary source and give it a verdict, and audit the inference from those facts before granting the conclusion.
Write in the language the user writes in.
1. Decompose the claim
If the user gave no claim, or a bare topic with nothing to check, ask one question for the text itself and stop.
Split the claim into three bins:
- Facts — statements the outside world can confirm or refute: numbers, events, quotes, attributions.
- Conclusions — what the claim infers from those facts.
- Value judgements — what it holds good, bad, or worth doing; no evidence settles these, so name them and set them aside.
A sentence usually mixes all three ("the study shows X, so we should Y") — cut at the seams rather than binning whole sentences. Rewrite each fact as one checkable proposition with its who, what, when and where. For a plan or proposal the facts are its premises and the conclusion is that the plan reaches its aim.
Done when every statement in the claim sits in exactly one bin and every fact is a single proposition specific enough to be found true or false.
2. Verify each fact
Check every fact with WebSearch and WebFetch, tracing it to its primary source. A page that repeats the number is a copy of the claim, not evidence for it; your own recollection is a claim to check, never a source. At the primary source read four things:
- Source — who originally produced it, and whether they are in a position to know.
- Sample — what was measured, on whom, how many, how selected.
- Date — when it was measured, and whether it is still current.
- Full context — what the source says around the quoted part; a true sentence lifted from its qualifications is the commonest way a fact goes wrong.
Tag each fact with exactly one verdict:
- Verified — the primary source says this, in this scope.
- Holds but must be narrowed — true for a smaller population, period, or definition than the claim states; write the narrowed form.
- Disputed — credible sources disagree; name who and on what.
- Insufficient evidence — no primary source found either way; record what you searched and what would settle it.
- Clearly wrong — the primary source contradicts it; write the correction.
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.
- 7d ago First seen · 72 lines · 33 tokens per session scan A e134985461c2
fact-check is a skill published in the GitHub repository coolTheWorld/evolution-skills (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,191 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
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…
iflytek-hyper-tts
A text-to-speech tool that turns written text into an MP3 recording. It can use an authorized voice and adjust speaking speed, volume, and pitch.