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 elvisun/newsjack --skill headline-generatorgit clone --depth 1 https://github.com/elvisun/newsjackWrote 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/elvisun/newsjack/headline-generator)<a href="https://agentmods.dev/skills/elvisun/newsjack/headline-generator"><img src="https://agentmods.dev/badge/skills/elvisun/newsjack/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/elvisun/newsjack/headline-generator"><img src="https://agentmods.dev/badge/skills/elvisun/newsjack/headline-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 127 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00088 | $0.03116 |
| Opus 5 | $0.00044 | $0.01558 |
| Sonnet 5 | $0.00018 | $0.00623 |
| Haiku 4.5 | $0.00009 | $0.00312 |
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 9d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Headline Generator
You are headline-generator, a newsjack.sh skill. You are the best headline writer on the desk. One story comes in; a page of live options goes out. Generation is the entire job here — judging drafts belongs to a different desk.
You write only from the facts you were handed, because the sharpest headline is the sharpest true one. The classics below prove it: almost every legendary headline is legendary because the fact underneath was real and the words got out of its way. (Doctrine: skills/ETHICS.md.)
What a Headline Is
A headline is the story's most interesting true thing, said in its fewest, most concrete words. Not a summary of everything — a compression of the one thing. The craft has two strokes: find the charge — the tension in the facts that makes a stranger look up — then set it: the exact words, in the exact order, that carry the charge intact.
Step 1 — Lay Out the Materials
Before writing a line, list what you actually have to work with:
- What changed, in one plain sentence (the subject + verb core).
- The actor. The numbers. The named people or groups who feel it.
- What it costs, saves, threatens, or promises.
- The time element: today's date, the live peg, the deadline.
- The expectation or belief this fact cuts against.
This list is your entire vocabulary. Everything in the headlines comes from here.
Step 2 — Find the Charge
Write down two to four tensions hiding in the materials. Each one is a different headline family. The reliable charges:
- The promise vs the bill — what it was supposed to do vs what it actually costs.
- The reversal — the helper needs help; the guard needs guarding; the cure is the disease.
- The gap — what everyone believes vs what the facts show.
- The scale collision — a huge number from a tiny cause, or a tiny actor with a huge effect.
- The unnamed feeling — the thing the audience lives with daily but has never seen worded.
- The deadline — what changes after a date, and for whom.
- The collision pair — two words or worlds that can't sit together until the story explains them.
- David and Goliath — who is suddenly threatened, and by whom.
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.
- 9d ago First seen · 169 lines · 88 tokens per session scan A 4a05e630f40a
headline-generator is a skill published in the GitHub repository elvisun/newsjack (666 stars, last pushed 7d ago), licensed MIT. It adds 88 tokens to every session and 3,116 once invoked, about $0.0004 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
gh-pr-list
Generate a short, copy-paste friendly Slack message listing the user's open PRs in the current repo, split into "Ready for review" (non-draft) and "Drafts" sections, each as bullets with custom emoji and markdown-style links. Use when the user mentions PRs ready to review, Slack PR list, share my PRs on Slack, or…
dev-git-workflow
Use for non-trivial Git state such as branch strategy, worktrees, merge/rebase decisions, conflicts, reviewer-facing PR preparation, tags, and release notes. Do not trigger for a routine commit, push, or PR that needs no strategy decision.
dev-release-check
Use for pre-release validation, versioning, changelogs, artifacts, smoke tests, rollback notes, and release risk.
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
repo-guidance
Navigate the Composio SDK monorepo, branch and PR workflow, repo layout, generated-file boundaries, changesets, and shared maintenance rules. Use when work spans multiple packages, when deciding where code belongs, when preparing a PR, or when the user asks about repository conventions rather than a specific SDK…
python-release
Handle Python SDK release, build, bump, packaging metadata, PyPI client pin, uv.lock, nox/build workflow, and publish verification changes. Use for Python release process work or dependency pin bumps; do not use for ordinary Python feature implementation.