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 headline-generatorgit 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/headline-generator)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/headline-generator"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/headline-generator/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/headline-generator"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/headline-generator.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 | $0.00029 | $0.01499 |
| Opus 5 | $0.00015 | $0.00749 |
| Sonnet 5 | $0.00006 | $0.00300 |
| Haiku 4.5 | $0.00003 | $0.00150 |
Grade A, and why
headline-generator 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Headline Generator
What This Skill Does
Generates a range of headline and subheadline options across different registers, lengths, and publication styles for a given article or feature.
When To Use This Skill
- You have a finished or near-finished article and need headline options before submitting to an editor
- You are stuck on a headline and want to break out of a single approach
- You need headlines calibrated to a specific publication's voice (tabloid, literary magazine, trade press, digital news)
- You want a main deck headline with subheadline options for long-form features
What You Need To Provide
Required: Article topic or a 2–4 sentence summary of the piece; publication type or audience (e.g., national newspaper, trade publication, literary magazine, digital media brand) Optional: Existing working headline you want to improve or use as reference; headline character limit; whether a subheadline (dek) is needed; any words or framing to avoid; tone directive (serious, provocative, wry, neutral)
How the Assistant Approaches This
- Identifies the article's core argument, revelation, or conflict — the one thing that makes this piece worth reading — and uses that as the anchor for all headline options
- Generates headlines across distinct structural approaches: declarative statement, question, imperative, ironic twist, "x of y" construction, and the clean noun-phrase format used by literary and long-form publications
- Calibrates register to the specified publication type — tabloid vocabulary and punctuation differ fundamentally from literary magazine style; trade press follows different conventions from consumer lifestyle
- For each main headline, writes a matching subheadline (dek) that adds the reporting context the main head omits
- Flags which options work best in print versus digital (SEO-aware headlines often sacrifice elegance; print heads can afford more wit)
- Closes with a one-sentence "Next Step" specifying which headline to take forward, whether to run social-media-excerpt to adapt the winning headline for platforms, and whether newsletter-teaser-writer is needed for distribution copy
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 · 110 lines · 29 tokens per session scan A bc08b6680d5b
headline-generator is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 29 tokens to every session and 1,499 once invoked, about $0.0001 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
xiaoyuzhou-podcast-notes
A workflow that turns a public Xiaoyuzhou FM podcast episode into structured Markdown notes and a saved transcript. Xiaoyuzhou FM is a Chinese podcast platform.
food-chain-ideation
10-minute pre-ship stress-test. Run this before you ship, not instead of shipping. Dynamically selects animal agents from a behavioral DNA library matched to the specific problem, each attacking under strict role-lock with zero shared context. Weakest eliminated each round, survivor absorbs the insight and evolves…
food-chain-pitch
Investor pitch stress-tester. Spawns adversarial agents from a pitch-specific behavioral DNA library. Each attacks the pitch narrative, financial model, or due diligence surface under strict role-lock. Elimination rounds harden the pitch. Works in Claude.ai, Claude Code, Cursor, Windsurf, Copilot with no dependencies.
food-chain-code
Adversarial architecture stress-tester. Selects attacker agents from a code-specific behavioral DNA library matched to the technical decision. Each attacks under strict role-lock. Weakest eliminated, survivor absorbs and evolves. Tests architecture decisions before a line of code is written. Works in Claude.ai, Claude…
apex-to-action
Converts food chain battle output into a 90-day execution plan. Takes the Evolved Idea, Unfair Advantage Statement, and Battle Log from any food chain battle and produces what to build first, what to validate before building, what to never build, and weekly milestones. The natural next step after any food chain…
food-chain-monitor
Re-stress-tests an idea that was previously battle-tested with food chain. Takes a Battle Log from a prior session plus a description of what changed, then runs a focused battle targeting only the NEW assumptions introduced by the change. Does not re-test what already survived. Works in Claude.ai, Claude Code, Cursor…