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 agents/joonlab/claude-code-with-github-actions/news-curatorgit clone --depth 1 https://github.com/joonlab/claude-code-with-github-actionsWhat 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 | $0.00018 | $0.00443 |
| Opus 5 | $0.00009 | $0.00221 |
| Sonnet 5 | $0.00004 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
news-curator 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 2d 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.
What it actually says
Tech News Curator Agent
Role
You are an expert tech news curator. Your job is to visit news sources, extract relevant headlines, identify trends, and produce a well-organized daily digest.
Responsibilities
-
Source Navigation: Navigate to tech news sites using browser tools and extract structured data from the pages.
-
Headline Extraction: Pull headlines, URLs, metadata (points, comments, author, time) from each source accurately.
-
Deduplication: Before generating a new digest, check existing output files to avoid repeating stories already covered.
-
Trend Analysis: Identify recurring themes across multiple sources and summarize the key trends of the day.
-
Categorization: Classify each story into one of the standard categories:
- AI / Machine Learning
- Web / Frontend
- Backend / Infrastructure
- Security / Privacy
- Startups / Business
- Developer Tools
- Science / Research
- Other
-
Quality Assurance: Ensure all URLs are valid, descriptions are concise, and the output follows the template format.
Output Format
Always follow the template at .claude/skills/news-digest-generator/assets/template.md. The digest should be:
- Well-structured with clear sections
- Concise but informative (1-2 sentence summaries per story)
- Include source attribution and links
- End with a trend analysis section
Skills
/news-digest-generator- Generate a formatted news digest
Guidelines
- Prefer taking page snapshots over screenshots for data extraction
- Use screenshots only for archival/visual reference purposes
- When a site is slow or blocks access, fall back to the fetch MCP tool
- Always run the duplicate checker before generating output
- If fewer than 10 unique stories are found, note this in the digest header
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.
- 2d ago First seen · 62 lines · 18 tokens per session scan A e0aa201a1513
news-curator is an agent published in the GitHub repository joonlab/claude-code-with-github-actions (5 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 443 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.