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 ur-grue/autopunk-media-skills --skill statistics-explainergit clone --depth 1 https://github.com/ur-grue/autopunk-media-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/ur-grue/autopunk-media-skills/statistics-explainer)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/statistics-explainer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/statistics-explainer/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/ur-grue/autopunk-media-skills/statistics-explainer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/statistics-explainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.01139 |
| Opus 5 | $0.00021 | $0.00570 |
| Sonnet 5 | $0.00008 | $0.00228 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade A, and why
statistics-explainer 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 10d 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.
Statistics Explainer
What This Skill Does
Rewrites a complex statistic — including percentage changes, relative risk, confidence intervals, medians, and index numbers — in plain language that a general audience can understand without sacrificing factual accuracy.
When To Use This Skill
- A statistic in your draft is accurate but you suspect a general reader will misread or misunderstand it
- You have received data containing terms like "relative risk," "odds ratio," "confidence interval," or "standard deviation" and need to explain them in copy
- An editor or sub-editor has flagged a statistic as confusing
- You want to check your own plain-language rewrite against a more rigorous version
What You Need To Provide
Required: The statistic as it appears in the source (exact wording or data point). The context — what the statistic is measuring and from what study, report, or dataset. Optional: The audience (general public, specialist readers, etc.); the publication register (tabloid, broadsheet, academic journal); any related comparison figure that might help contextualise it.
How the Assistant Approaches This
- Identifies the statistical concept being used and checks for common misinterpretation traps (e.g. relative vs absolute risk, percentage point vs percentage change).
- Rewrites the statistic using plain numbers and concrete comparisons — avoiding jargon, passive constructions, and ambiguous framing.
- Flags any cases where the plain-language version risks oversimplification, and suggests a brief accuracy note if needed.
Output Format
Two to three rewrite options, each one to three sentences. A brief note explaining the key misinterpretation risk in the original. Where relevant, a suggested accuracy caveat (one sentence) to include alongside the plain-language version. No tables or bullet lists in the output — the rewrites should read as they would appear in an article.
Quality Criteria
- Every rewrite is factually equivalent to the original — no inflating or deflating the finding
- No jargon introduced in the plain-language version
- At least one concrete comparison or real-world anchor (e.g. "1 in 5," "the equivalent of filling Wembley Stadium twice")
- The misinterpretation risk is named specifically, not generically
- Accuracy note is included where genuine oversimplification risk exists
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 72 lines · 42 tokens per session scan A e7fdd4dd9678
statistics-explainer is a skill published in the GitHub repository ur-grue/autopunk-media-skills (30 stars, last pushed 10d ago), licensed MIT. It adds 42 tokens to every session and 1,139 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 2026-08-30.
Other skills, from other repositories
secure-auth
Secure authentication patterns (OWASP, NIST). Use for login, registration, password reset, sessions, JWT, OAuth, MFA, passkeys.
visual-explainer
HTML explainers, diagrams, architecture, timelines, source maps, slide decks, comparison tables, recaps, plan and diff reviews.
foia-requests
FOIA and public records workflows. Use when drafting requests, tracking submissions, checking exemptions, or appealing denials.
academic-writing
Scholarly writing and research compliance. Use for CRediT, preregistration, Plan S, Nelson Memo, preprints, ORCID, LLM disclosure.
page-monitoring
Web page change detection, availability tracking, and RSS feed generation. Use to monitor changes, downtime, or make a feed.
web-archiving
Web archiving and retrieval via Wayback Machine and Archive.today. Use to preserve content, reach dead pages, or save evidence.