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 agentmods add skills/eventregistry/newsapi-mcp/skillnpx skills add EventRegistry/newsapi-mcp --skill skillgit clone --depth 1 https://github.com/EventRegistry/newsapi-mcpWrote 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/eventregistry/newsapi-mcp/skill)<a href="https://agentmods.dev/skills/eventregistry/newsapi-mcp/skill"><img src="https://agentmods.dev/badge/skills/eventregistry/newsapi-mcp/skill.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00042 | $0.05247 |
| Opus 5 | $0.00021 | $0.02624 |
| Sonnet 5 | $0.00008 | $0.01049 |
| Haiku 4.5 | $0.00004 | $0.00525 |
Grade A, and why
news 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 4d 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
News Research Skill
Research news topics end-to-end using the NewsAPI MCP server. This skill orchestrates the right tool sequence for different question types and formats findings for export.
Usage
/news "What's happening with AI regulation?"— run a full research workflow/news— interactive mode, asks for the research question
Rules
- Sequential requests only — never fire multiple NewsAPI calls in parallel (max 5 concurrent allowed by API, but sequential is safer and required by server instructions)
- Deduplicate by default — use
isDuplicateFilter: "skipDuplicates"in all scan steps - Track usage — read the "Tokens used" footer from every response and report totals at the end
Workflow: suggest → scan → triage → retrieve
Step 1: Suggest — resolve names to URIs
suggest({type: "concepts", prefix: "Tesla"}) → get conceptUri
Always resolve entity names before searching. Keyword search is a fallback.
Step 2: Scan — retrieve titles only
search_articles({conceptUri: "<uri>", articlesCount: 100, articleBodyLen: 0, isDuplicateFilter: "skipDuplicates"})
Fetch up to 100 articles with NO bodies — returns only titles, dates, sources, and URIs. Very token-efficient. Use isDuplicateFilter: "skipDuplicates" to remove wire syndication noise.
Step 3: Triage — assess relevance
Read the titles from step 2. Select the articles relevant to the user's question by their URIs. If too few relevant results, paginate (articlesPage: 2) and repeat step 2.
Step 4: Retrieve — get full details
get_article_details({articleUri: ["<uri1>", "<uri2>", "<uri3>", ...]})
Pass up to 100 URIs per call. If you have more than 100 relevant articles, batch them into multiple calls of 100 URIs each. Add includeFields only for data you need.
Choosing search_articles vs search_events
- search_articles → individual articles, full text, specific sources
- search_events → high-level overview, deduplicated event clusters, "what's happening with X"
What ships with it
10 files 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.
- templates/adverse-media.md 1.1 KB
- templates/company-intel.md 1.0 KB
- templates/economic.md 971 B
- templates/findings.md 669 B
- templates/geopolitical.md 1.2 KB
- templates/investing.md 1004 B
- templates/political.md 960 B
- templates/research.md 1.3 KB
- templates/sentiment.md 698 B
- templates/supply-chain.md 1.1 KB
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.
- 4d ago First seen · 324 lines · 42 tokens per session scan A 46a31ccbd727
news is a skill published in the GitHub repository EventRegistry/newsapi-mcp (1 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 5,247 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 2026-08-31.
Other skills, from other repositories
the-news
This skill gives agents access to the main headlines of many newspapers and news sites, across 20 countries, via a public API. The API has two modes: a live mode, updated in near real-time, and an archive mode that lets you fetch the headlines from a given moment in time. In both modes, the endpoint returns a JSON…
the-news
This is a global news skill for latest news, breaking news, world news, current events, and news headlines. It gives agents a live multi-source news snapshot and a searchable headline archive across 20 countries via a public API.
syft-news-pipeline
Coordinate Syft-only personalized news workflows in Codex or Claude Code using only syft following, syft top, and syft search. Use when Codex needs to decide or run the right path for building profile artifacts, capturing durable guidance, drafting daily briefings, generating trunk-branch storyline trees, or…
syft-cli-assistant
Use when the user needs help installing, authenticating, troubleshooting, or using the local syft CLI for Syft AI news workflows. Trigger for first-time setup, syft login or syft status, followed-topics inspection, top stories, personal search, global search, Codex skill installation via syft install-skill, or any…
syft-storyline-tree
Use when the user wants to turn Syft CLI news into a trunk-branch storyline tree, attach timelines, render markdown plus html plus json outputs, or prepare branches for later Syft search extension in Codex or Claude Code without local Python scripts. Also use when the user asks for event trees, storyline timelines…
syft-daily-briefing
Use when the user wants a personalized daily news briefing from Syft CLI following topics in Codex or Claude Code without relying on local Python scripts. Also use when the user wants a profile-aware editorial edition, issue clustering, mainline plus supplement structure, stronger interest coverage, or a richer daily…