news-monitoring

news-monitoring is a skill for Claude Code, Codex from moonlight-lupin/agent-skills. It costs 42 tokens per session (3,684 once invoked), scanned A, original, MIT.

A workflow for regularly searching the web for news about a chosen subject and preparing the results as a digest. It can use sources in several languages and deliver the digest to a channel or document system.

In plain words
What is it for?
For tracking topics by region or angle, selecting recent articles, summarizing headlines, and sending recurring updates.
Why use it?
It removes the need to repeat searches, compare sources, and format updates by hand.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit For tracking topics by region or angle, selecting recent articles, summarizing headlines, and sending recurring updates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/moonlight-lupin/agent-skills/news-monitoring
Install

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.

Any agent
npx skills add moonlight-lupin/agent-skills --skill news-monitoring
Clone the repo
git clone --depth 1 https://github.com/moonlight-lupin/agent-skills

Made for: Claude Code, Codex.

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 news-monitoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/news-monitoring/github.svg)](https://agentmods.dev/skills/moonlight-lupin/agent-skills/news-monitoring)
Your own site
<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.

agentmods 80×15 button for news-monitoring

Your own site · 80×15
<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>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,684 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
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 $0.00042 $0.03684
Opus 5 $0.00021 $0.01842
Sonnet 5 $0.00008 $0.00737
Haiku 4.5 $0.00004 $0.00368

Measured 12d ago against content hash 10dfc8c84bab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.**
research/news-monitoring/SKILL.md · 274 lines

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.

Read the full file on GitHub · 274 lines

Files

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.

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. 12d ago First seen · 274 lines · 42 tokens per session scan A 10dfc8c84bab

Subscribe to this mod's changes

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.