agentmods.dev

source-analysis

source-analysis is a skill for Claude Code from EventRegistry/newsapi-mcp. It costs 0 tokens per session (958 once invoked), scanned A, original, MIT.

A news-source analysis skill that uses NewsAPI tools to compare how outlets cover a topic, measure the tone of coverage, and identify which sources or countries contribute to it.

In plain words
What is it for?
It helps compare outlets, study sentiment around an organisation or topic, examine framing vocabulary, and map the sources covering a story.
Why use it?
It makes differences in coverage, wording, sentiment, and source reach easier to examine than reading outlets one by one.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the newsapi plugin — 6 skills, 1 MCP server shipped together

not rated 3repo changed 22d ago A scan 0 tokens original MIT

Good fit It helps compare outlets, study sentiment around an organisation or topic, examine framing vocabulary, and map the sources covering a story.

Compare 6 skills from other repositories ↓
View source ↗ EventRegistry/newsapi-mcp npmjs.com
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add EventRegistry/newsapi-mcp
Claude Code
/plugin install newsapi

Made for: Claude Code.

Or install newsapi, the plugin that ships this one along with the rest of its 6 skills, 1 MCP server.

Wrote 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.

agentmods badge for source-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/eventregistry/newsapi-mcp/source-analysis/github.svg)](https://agentmods.dev/skills/eventregistry/newsapi-mcp/source-analysis)
Your own site
<a href="https://agentmods.dev/skills/eventregistry/newsapi-mcp/source-analysis"><img src="https://agentmods.dev/badge/skills/eventregistry/newsapi-mcp/source-analysis/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.

agentmods 80×15 button for source-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/eventregistry/newsapi-mcp/source-analysis"><img src="https://agentmods.dev/badge/skills/eventregistry/newsapi-mcp/source-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 958 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00958
Opus 5.5 $0.00000 $0.00383
Sonnet 5.5 $0.00000 $0.00192
Haiku 4.5 $0.00000 $0.00096

Measured 22d ago against content hash c771acfe5b39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

source-analysis 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 22d 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.

skills/source-analysis/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source analysis

Read ${CLAUDE_PLUGIN_ROOT}/skills/_reporting.md first: it holds the search workflow, kinds, aggregates, filters, citation rules, report skeleton and usage footer.

Usage

  • /newsapi:source-analysis "Reuters vs Fox News on tariffs" — source comparison
  • /newsapi:source-analysis "sentiment around Tesla" — sentiment
  • /newsapi:source-analysis "who covers the Panama Canal?" — coverage landscape

Aggregates do the measuring; article scans supply the examples. Comparing groups of outlets or countries in one call is a query with sourceUri / sourceLocationUri under $or (grammar in the shared reference).

Source comparison

  1. suggest({type: "concepts", prefix: "<topic>"}); suggest({type: "sources", prefix: "<source>"}) for each outlet. No outlets named → search({kind: "articles", conceptUri, resultType: "sourceAggr"}) and pick the top ones, or compare countries with sourceLocationUri
  2. For each outlet: search({kind: "articles", conceptUri, sourceUri, resultType: "sentimentAggr"}) and "keywordAggr" (framing vocabulary); "timeAggr" if timing matters
  3. For each outlet: search({kind: "articles", conceptUri, sourceUri, count: 50, articleBodyLen: 0, isDuplicateFilter: "skipDuplicates"}), triage representative articles
  4. get_article_details({articleUri: [...], includeFields: "sentiment"})
  5. Report with the source comparison template

Sentiment

  1. suggest({type: "concepts", prefix: "<entity>"})
  2. search({kind: "articles", conceptUri, lang: "eng", resultType: "sentimentAggr"}) for the distribution and "timeAggr" for the volume curve (sentiment is scored for English articles only)
  3. Representative articles per pole: search({kind: "articles", conceptUri, lang: "eng", count: 30, articleBodyLen: 0, isDuplicateFilter: "skipDuplicates", options: {minSentiment: 0.3}}) and the same with options: {maxSentiment: -0.3}; triage a few from each
  4. get_article_details({articleUri: [...], includeFields: "sentiment"})
  5. Drivers: search({kind: "mentions", conceptUri, count: 50, resultType: "eventTypeAggr"}) tells which kinds of happenings dominate the coverage
  6. Report with the sentiment template

Read the full file on GitHub · 80 lines

Changes

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.

  1. 22d ago Changed · -52 tokens per session c771acfe5b39
  2. 24d ago First seen · 80 lines · 52 tokens per session scan A 622c5fb845af

Subscribe to this mod's changes

source-analysis is a skill published in the GitHub repository EventRegistry/newsapi-mcp (3 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 958 tokens. 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 2026-10-14.

Analytics and metricsResearchmcpnewsapi
Related

source-analysis compared with skills from other repositories

source-analysis next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
source-analysisEventRegistry/newsapi-mcpSkill310d agoMITA0Claude Code
the-newsSFKislev/The-NewsSkill164mo agoMITA31Claude Code, Codex
the-newsSFKislev/The-NewsSkill164mo agoMITA31Claude Code, Codex
syft-news-pipelineSolatrader/syft-news-skillsSkill55mo agoApache-2.0A89Codex
syft-cli-assistantSolatrader/syft-news-cli-assistantSkill25mo agoApache-2.0A90Codex
syft-storyline-treeSolatrader/syft-news-skillsSkill55mo agoApache-2.0A85Claude Code, Codex
syft-daily-briefingSolatrader/syft-news-skillsSkill55mo agoApache-2.0A73Claude Code, Codex