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 article-summary-writergit 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/article-summary-writer)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/article-summary-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/article-summary-writer/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/article-summary-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/article-summary-writer.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 | $0.01721 |
| Opus 5 | $0.00021 | $0.00860 |
| Sonnet 5 | $0.00008 | $0.00344 |
| Haiku 4.5 | $0.00004 | $0.00172 |
Grade A, and why
article-summary-writer 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 8d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Article Summary Writer
What This Skill Does
Writes a concise summary, standfirst, abstract, or deck for a completed article at a specified length and format — capturing the essential argument and news value without spoiling the reading experience.
When To Use This Skill
- You need a standfirst or deck for a published article and the editor wants it in under 50 words
- You're preparing newsletter copy and need a two-sentence summary of each article to drive click-through
- An article needs an abstract for a database, archive, or academic citation
- You're writing social media preview text and need the article's core argument distilled to a single sentence
- The CMS requires a meta description and you want it to reflect the article's substance, not just keywords
What You Need To Provide
Required:
- The full article text (or a detailed summary of its content, argument, and conclusion)
- The summary format: standfirst, deck, abstract, newsletter teaser, meta description, or general summary
Optional:
- Target length (specific word count or character count; defaults vary by format — see Output Format)
- Tone: formal, conversational, urgent, or neutral
- Whether the summary should avoid revealing the article's conclusion (important for opinion pieces and investigations)
- Target audience if different from the article's primary readership
How the Assistant Approaches This
-
Identifies the article's core argument. Before writing, isolates the single most important claim, finding, or narrative the article makes. This is not always the lede — sometimes the real argument emerges in the middle of the piece. The summary leads with this core, not with setup or background.
-
Matches the format conventions. Each summary type has distinct conventions:
- Standfirst/deck: Complements the headline — adds the "why should I read this" that the headline implies but doesn't deliver. Never repeats the headline's phrasing.
- Abstract: States the subject, method, findings, and significance in neutral academic register.
- Newsletter teaser: Creates a curiosity gap — gives enough to interest, withholds enough to compel the click.
- Meta description: Front-loads the most important information within 155 characters for search engine display.
- General summary: Captures the article's argument, key evidence, and conclusion in proportion to the specified length.
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.
- 8d ago First seen · 111 lines · 42 tokens per session scan A c6fa31f28547
article-summary-writer is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 42 tokens to every session and 1,721 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 2026-09-04.
Other skills, from other repositories
cultural-heritage-summary
Produces structured, citation-ready summaries of legal developments in cultural heritage protection covering repatriation, site protection, illicit trafficking, and treaty updates. Use when tracking heritage law, preparing government or NGO briefings, or summarizing international and national decisions. Trigger…
mckinsey-market-research-deck
End-to-end playbook for producing a top-tier, McKinsey-style market-research deck (HTML page-turning presentation + print-ready PDF) for a brand or product category. Covers the research methodology (TAM/SAM/SOM bottom-up, Good/Better/Best framework, competitor profiling, customer pain points, unit economics, business…
mckinsey-deck
Turn any content into a top-tier McKinsey-style deck — a 1280×720 page-turning HTML presentation that also prints to a clean per-slide PDF. Use when the user wants a "McKinsey-style deck / presentation", a polished slide deck or PDF from notes/content, an executive/board/investor deck, or to "make slides / a deck / a…
deck-factory
A design system and working method for hand-building polished HTML presentation slides from a brief or script.
cyber-law-compliance-summary
Produces structured cyber law compliance memoranda covering GDPR, CCPA, state privacy laws, and sector-specific regulations for US and EU operations. Includes Bluebook citations, jurisdiction comparison tables, penalty exposure, and regulatory trends. Use when advising on digital operations compliance, privacy program…
youtube-seo-competitor
Advanced YouTube competitor intelligence. Detects direct competitors, extracts winning title/thumbnail/hook patterns from transcripts, infers retention strategies from pacing, correlates posting cadence with performance, and identifies format-market-fit gaps. Use when user says "YouTube competitor analysis", "what are…