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 moonlight-lupin/agent-skills --skill news-monitoringgit clone --depth 1 https://github.com/moonlight-lupin/agent-skillsWrote 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/moonlight-lupin/agent-skills/news-monitoring)<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/news-monitoring"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/news-monitoring/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/moonlight-lupin/agent-skills/news-monitoring"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/news-monitoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 166 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00042 | $0.03684 |
| Opus 5 | $0.00021 | $0.01842 |
| Sonnet 5 | $0.00008 | $0.00737 |
| Haiku 4.5 | $0.00004 | $0.00368 |
Grade A, and why
news-monitoring scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Advanced option: SearXNG direct curl for news-specific filters.** How it starts
The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
News Monitoring & Digest Delivery
Set up recurring topic/news monitoring that searches the web for recent articles, compiles a headline digest, and delivers it to a messaging channel or document pipeline.
Workflow
Step 1 — Define Topic
Work with the user to define:
- Subject: what to monitor (e.g. PBSA in Hong Kong, AI regulation, self-hosting tools)
- Geography: which region(s) matter (e.g. Hong Kong, Singapore, global)
- Angles: which aspects to track — investment/deals, policy/regulation, supply/pipeline, occupancy/rental, general commentary
- Velocity: how fast-moving the field is — determines acceptable article age (see Step 5)
Step 2 — Create Search Keywords
Build search queries from the topic definition:
- Multi-angle: one query per angle (investment, policy, supply, etc.)
- Multi-language: English keywords + native language keywords for each geography
- Time-bounded: specify recency in the query where possible (e.g. "2026", "latest")
- Keep queries concise — 3-7 terms works best. Overly long queries return thin results.
Step 3 — Select Sources
Identify which sources matter for the topic and geography:
- English-language: international outlets, local English press, industry publications
- Native-language: local press in the geography's primary language(s) — these often break news first
- Industry-specific: trade publications, research houses, REIT/sector-specific sites
- Closed-ecosystem platforms (小红书, 抖音, 微信公众号): content is NOT web-indexed. Be upfront about this limitation — options are manual monitoring or third-party analytics tools.
Record the source list in the topic's reference file (see Reference Files section).
Step 4 — Run Searches
Date grounding (mandatory). Before running any search, ground the model in the real current date. LLMs default to training-cutoff years in queries — this produces stale results. Inject:
Today's date is {current date as "DD Month YYYY"}. When a search query needs a year or refers to "latest"/"current"/"this year", use {current year} or relative wording — never a year inferred from training data.
What ships with it
4 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.
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.
- 12d ago First seen · 274 lines · 42 tokens per session scan A 10dfc8c84bab
news-monitoring is a skill published in the GitHub repository moonlight-lupin/agent-skills (64 stars, last pushed 5d ago), licensed MIT. It adds 42 tokens to every session and 3,684 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
SoloFlow
A meta-skill that silently watches your workflows and automatically generates reusable Hermes skills from them.
hermes-tweet
Use Xquik in Hermes Agent for public X research, monitoring, thread summaries, creator discovery & approved actions. Not affiliated with X Corp. Use when the user requests X data or a named action. Trigger with "search X", "monitor X", "post tweet", or "X trends".
image
Create or optimize marketing images, social graphics, product mockups, banners, cover art, listing visuals, brand assets, image prompts, WebP files, and OG images.
video
Plan and produce video with available AI tools or programmatic frameworks. Use for video prompts, avatars, explainers, demos, templates, pipelines, and generation.
content-research-writer
Research, outline, draft, cite, and revise articles, reports, tutorials, newsletters, and case studies with traceable sources and preserved voice.
content-analysis
Analyze articles, documents, videos, podcasts, and transcripts for arguments, evidence, themes, assumptions, contradictions, insights, and unanswered questions.