daily-news

daily-news is a skill for Claude Code from XBlueSky/vatt-ghern. It costs 165 tokens per session (18,289 once invoked), scanned A, original, MIT.

An automated workflow for collecting current technology news, removing duplicates, and writing roundup or feature posts for the vatt-ghern blog. It can also prepare weekly and monthly summaries from earlier posts.

In plain words
What is it for?
Use it to run daily news routines, create weekly or monthly rollups, generate the required HTML files, validate them, and open a review pull request.
Why use it?
It removes the repeated work of finding suitable stories, checking the archive, organizing them, and preparing posts for review.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

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 vatt-ghern plugin — 1 skill, 3 commands, 1 hook shipped together

Good fit Use it to run daily news routines, create weekly or monthly rollups, generate the required HTML files, validate them, and open a review pull request.

Compare 6 skills from other repositories ↓
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 XBlueSky/vatt-ghern
Claude Code
/plugin install vatt-ghern

Made for: Claude Code.

Or install vatt-ghern, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 1 hook.

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 daily-news

README.md
[![agentmods](https://agentmods.dev/badge/skills/xbluesky/vatt-ghern/daily-news/github.svg)](https://agentmods.dev/skills/xbluesky/vatt-ghern/daily-news)
Your own site
<a href="https://agentmods.dev/skills/xbluesky/vatt-ghern/daily-news"><img src="https://agentmods.dev/badge/skills/xbluesky/vatt-ghern/daily-news/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 daily-news

Your own site · 80×15
<a href="https://agentmods.dev/skills/xbluesky/vatt-ghern/daily-news"><img src="https://agentmods.dev/badge/skills/xbluesky/vatt-ghern/daily-news.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 165 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 18,289 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.
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 $0.00165 $0.18289
Opus 5 $0.00082 $0.09144
Sonnet 5 $0.00033 $0.03658
Haiku 4.5 $0.00016 $0.01829

Measured 2d ago against content hash effaa5baeb46, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

daily-news 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check-claim-ledger.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

sleep 2 && curl -s -o /dev/null -w "%{http_code}\n" http://localhost:8080/
skills/daily-news/SKILL.md · 1,476 lines

How it starts

The opening of the file, as written. The whole thing — 1,476 lines — stays where its author put it; the contents beside it link to each section on GitHub.

daily-news

Curate today's tech news for the vatt-ghern blog and publish it as bespoke HTML posts. Adopt a senior-tech-lead persona, fetch from a priority source list, score and de-duplicate (exact source URL / news_id against the full archive, fuzzy title similarity against the past 7 days), write one roundup and up to three deep-stories, and open a pull request for human review.

When this skill runs

Three invocation paths converge here:

  • Daily/vatt-ghern:daily-news (defined in ${CLAUDE_PLUGIN_ROOT}/commands/daily-news.md). Executes the full 9-step workflow below.
  • Weekly rollup/vatt-ghern:weekly (Monday morning). Skips Steps 2–6; resolves the covered ISO week (Mon–Sun, the one that just ended) via scripts/weekly-window.mjs; reads it via scripts/load-past-roundups.mjs --days=7 --end=<Sunday>; computes week-over-week delta via scripts/decisions/weekly-delta.mjs --end=<Sunday>; authors one weekly.html using the weekly-rollup archetype.
  • Monthly rollup/vatt-ghern:monthly (first of month). Same pattern as weekly but --days=<28..31> and monthly-rollup archetype.
  • Routine fallback: Claude Routines invoking the repo may load this SKILL.md directly when the slash command is unavailable. The routine inspects its own schedule to decide daily vs weekly vs monthly.

For weekly/monthly invocations, read the rollup archetype reference (references/archetypes/weekly-rollup.md or references/archetypes/monthly-rollup.md) — it spells out which workflow steps to skip and what the output looks like.

Do not author daily news posts without this skill. Ad-hoc posts drift from the archetype rules and break the dedup invariants that future days depend on.

Required reading before authoring

Read these references before producing output. They are the single source of truth — do not re-derive their contents:

  • references/persona.md — Voice (measured, curious, materially-rooted), five priority domains, what earns inclusion vs. what doesn't, punctuation rules ( not :; —— not ).
  • references/zh-tw-prose.md — 中文 prose 規則(AI 套話、黑話、 翻譯腔、節奏、台灣用語)。鐵律:去 AI 味靠刪與改寫,不得捏造細節。
  • references/sources.md — Tier-1 through Tier-5 source list with priority order. HackerNoon is the primary signal.
  • references/archetypes.md — Required HTML structure for roundup and deep-story, sidecar JSON schema, content rules, scoring rubric.
  • references/anti-duplication.md — Dedup rules: exact source-URL / news_id against the full archive, fuzzy title similarity against the past 7 days, and how to handle near-duplicates.
  • references/design-system.md — Color tokens, font stacks, component classes, read-tracking attribute conventions, SVG patterns.
  • references/widget-isolation.md — CSS / ID / JS scoping contract for inline SVG widgets.

Read the full file on GitHub · 1,476 lines

Files

What ships with it

60 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. 2d ago Changed · +2 lines effaa5baeb46
  2. 12d ago First seen · 1,474 lines · 165 tokens per session scan A a11cd6778b1c

Subscribe to this mod's changes

daily-news is a skill published in the GitHub repository XBlueSky/vatt-ghern (5 stars, last pushed yesterday), licensed MIT. It adds 165 tokens to every session and 18,289 once invoked, about $0.0008 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 2026-08-31.