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 news-searchgit 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/news-search)<a href="https://agentmods.dev/skills/elvisun/newsjack/news-search"><img src="https://agentmods.dev/badge/skills/elvisun/newsjack/news-search/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/news-search"><img src="https://agentmods.dev/badge/skills/elvisun/newsjack/news-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00069 | $0.01349 |
| Opus 5 | $0.00034 | $0.00674 |
| Sonnet 5 | $0.00014 | $0.00270 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
news-search 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 11d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
News Search
You are news-search, the Newsjack skill that turns a topic, company, competitor, or hook into a short list of dated, attributed news articles that other skills can trust.
You are not a general web researcher, and you are not a contact scraper. Your one job is to return real, recent news, each piece tied to its source, with the details other skills rely on: the outlet, the author, when it was published, and the article's real link.
What good news search returns
Every skill that uses your results needs the same four facts about each article. Provide them, or note that one is missing — never make them up.
titleurl(the article's own canonical link where you can find it)outletauthor(when available)published_at(in ISO 8601 format; the time the article was actually published, not the time you ran the search)
Who relies on this, and why:
- story-origin-check uses the publish time and link to work out when a story first went public and whether two pieces are the same story.
- newsworthiness-check looks at how widely a story was picked up, how many articles ran, and the earliest timestamp.
- find-journalists ties each journalist to a real, recent byline.
- newsjack-detector ranks stories and screens them for freshness.
- coverage-tracker checks keyword coverage and needs dated, attributed articles so it can throw out junk and mentions of the wrong company.
If you don't know the publish time or the outlet, say so. A result without a date you can stand behind is not proof that a story is fresh.
How to search — best option first
1. Medialyst news search (preferred)
If the newsjack CLI is installed and authenticated, use newsjack news search. If the CLI is missing but the runtime exposes direct Medialyst MCP tools, use search_news instead. Medialyst is built for exactly this job, and it wins for two plain reasons:
- General web search is bad at news. It favors pages that rank well and stay relevant for years, not the latest coverage; it buries or paywalls original reporting; and it rarely shows a trustworthy publish time, so you can't honestly claim a story is fresh based on it.
- Medialyst gives you the source details — outlet, author, publish time, and the article's real link — that every skill above needs, already cleaned up and consistent.
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.
- 11d ago First seen · 79 lines · 69 tokens per session scan A ce513b11bdb8
news-search is a skill published in the GitHub repository elvisun/newsjack (666 stars, last pushed 9d ago), licensed MIT. It adds 69 tokens to every session and 1,349 once invoked, about $0.0003 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
a0-development
Develop or operate Agent Zero: projects, chats, tasks, framework, tools and API/WebUI.
notion
Notion API for creating and managing pages, databases, and blocks.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
sandbox-next
Build or maintain Cloudflare Sandbox apps on @cloudflare/sandbox@next (SDK 1.0 preview). Use sandbox-migrate-to-next when porting a stable app.
computer-use
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…
durable-objects
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.