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 data-story-findergit 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/data-story-finder)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/data-story-finder"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/data-story-finder/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/data-story-finder"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/data-story-finder.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 | $0.00039 | $0.01683 |
| Opus 5 | $0.00019 | $0.00842 |
| Sonnet 5 | $0.00008 | $0.00337 |
| Haiku 4.5 | $0.00004 | $0.00168 |
Grade A, and why
data-story-finder 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 12d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Story Finder
What This Skill Does
Identifies the newsworthy story or stories hidden inside a dataset before any writing begins — surfacing angles, outliers, trends, and comparisons that are genuinely publishable.
When To Use This Skill
- You have a dataset but are unsure which part of it is actually news
- You need to pitch a data story to an editor and want compelling angles, not just descriptions
- You want to stress-test a dataset before committing reporting time to a particular angle
- A PR or institution has released data and you want to find what they are not publicising
What You Need To Provide
Required: A description of what the dataset contains — column headers, row count, time period covered, and source. Include a small representative sample (5–20 rows) if possible. Optional: The institution or event the data came from; any story hypothesis you already have; publication type and audience.
How the Assistant Approaches This
- Reads the dataset description and sample to understand the structure, variables, and coverage period.
- Applies five standard news-value lenses: magnitude, change over time, geographic variation, outliers, and hidden/buried comparisons.
- Generates a ranked list of potential story angles with a plain-language summary of what makes each newsworthy, what data point supports it, and what additional reporting would be needed to publish it.
Output Format
A structured document with: a one-paragraph overview of what the dataset does and doesn't show, followed by three to six numbered story angles. Each angle includes: a one-sentence story pitch, the specific data point or pattern that supports it, a confidence note (strong / tentative / requires verification), and one or two reporting questions to pursue next. Plain language throughout — no statistical jargon unless necessary, and always explained when used.
Quality Criteria
- At least three distinct angles, not variations of the same angle
- Every angle is grounded in a specific data point from the sample, not a generalisation
- Confidence ratings are honest — tentative findings are marked as such
- No angle claims significance beyond what the data actually shows
- Reporting questions are concrete and actionable, not generic
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.
- 12d ago First seen · 92 lines · 39 tokens per session scan A 9f53d27e6b6b
data-story-finder is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 39 tokens to every session and 1,683 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.
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.
newsletter-publishing
Email newsletter workflows. Use when creating newsletters, building subscriber lists, designing templates, or tracking engagement.
web-ui-best-practices
Signs of taste in web UI. Use when building or reviewing web interfaces, dashboards, SaaS apps, or internal tools.