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 dataset-summary-briefgit 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/dataset-summary-brief)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/dataset-summary-brief"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/dataset-summary-brief/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/dataset-summary-brief"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/dataset-summary-brief.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 | $0.00045 | $0.01603 |
| Opus 5 | $0.00023 | $0.00801 |
| Sonnet 5 | $0.00009 | $0.00321 |
| Haiku 4.5 | $0.00005 | $0.00160 |
Grade A, and why
dataset-summary-brief 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dataset Summary Brief
What This Skill Does
Produces a structured summary of what a dataset contains, what it covers, what its limitations are, and what story angles it could plausibly support — written as a briefing document for a journalist or editor.
When To Use This Skill
- You have received a new dataset and need to assess its news potential quickly before committing reporting time
- You need to brief an editor, producer, or commissioning colleague on what a dataset does and doesn't contain
- You are handing off a dataset to another journalist and need to document what you found
- You want to identify data gaps before deciding whether additional FOI requests or data collection are needed
What You Need To Provide
Required: A description of the dataset — source, title or file name, number of rows and columns, time period covered, geographic scope, and a list of column names with brief descriptions of what each contains. Optional: A small representative data sample; any known issues with the data (missing values, format inconsistencies); the context in which the data was obtained (FOI response, published report, leaked document).
How the Assistant Approaches This
- Reviews the structure description and identifies the key variables, time dimensions, and geographic granularity of the dataset.
- Assesses the dataset's completeness and potential limitations — missing periods, incomplete geographies, definitional ambiguities, and likely data quality issues.
- Writes a structured brief covering: what the dataset is and where it came from, what it can and cannot show, and three to five story angles it could support.
Output Format
A one-page briefing document (approximately 400–600 words) structured under four headings: What This Dataset Is, What It Covers, Limitations and Caveats, and Potential Story Angles. Tone: direct and editorial — written for a journalist colleague, not a data scientist. No statistics formulae. Plain language throughout.
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 · 105 lines · 45 tokens per session scan A 3b048318d522
dataset-summary-brief is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 45 tokens to every session and 1,603 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.