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 davidtoby/agent-skills --skill wechat-business-news-crongit clone --depth 1 https://github.com/davidtoby/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/davidtoby/agent-skills/wechat-business-news-cron)<a href="https://agentmods.dev/skills/davidtoby/agent-skills/wechat-business-news-cron"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/wechat-business-news-cron/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/davidtoby/agent-skills/wechat-business-news-cron"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/wechat-business-news-cron.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00047 | $0.02834 |
| Opus 5 | $0.00023 | $0.01417 |
| Sonnet 5 | $0.00009 | $0.00567 |
| Haiku 4.5 | $0.00005 | $0.00283 |
Grade A, and why
wechat-business-news-cron 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Daily News Digest Cron (WeChat / Feishu)
Use this when a user wants recurring current-affairs digests delivered to WeChat or Feishu, especially morning/evening briefings in Chinese with a polished business-brief style.
When to use
- User wants a daily or twice-daily news digest
- Delivery target is WeChat / Weixin, Feishu, or the current chat thread
- The user cares about presentation quality, not just content retrieval
- The requested schedule is in the user's timezone rather than the environment timezone
- There may already be older digest jobs that should be removed or replaced
Companion skills
google-news-rss-digesting: For the actual news-gathering and canonical-URL-resolution workflow. Load this skill during digest execution to handle Google News RSS → browser topic pages → source homepage verification → canonical URL extraction.multi-search-engine: For broader search queries across 17 engines when RSS alone isn't enough.rss-news-fetcher: Simpler alternative for BBC/Guardian/SCMP RSS-only fetching in restricted environments. Now covers CNBC, NPR, TechCrunch, NYT, WSJ, plus a hybrid RSS+browser workflow for harvesting article detail from JS-rendered news sites.
Core lessons learned
This is not just "create a cron job". In practice, the task often requires:
- checking existing cron jobs to avoid duplicate delivery
- converting the user's requested local time into the environment timezone manually
- using cron syntax instead of natural-language timezone strings
- choosing the correct delivery target (
weixinworked better than relying on generic origin delivery) - iterating the prompt format until the output feels like a polished Chinese business briefing rather than a low-end bullet dump
Important platform behavior
1) Hermes cron schedule parsing
Do not assume timezone-aware natural language schedules will work. A schedule like:
every day at 7:00 Europe/Londonmay fail with an invalid duration/schedule error.
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.
- 9d ago First seen · 307 lines · 47 tokens per session scan A 276801981e5c
wechat-business-news-cron is a skill published in the GitHub repository davidtoby/agent-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 2,834 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
find-skills
Use when automatically discover, evaluate, and activate community skills when local skills don't cover user needs. Includes credibility scoring and safety checks for complete OpenClaw self-sufficiency.
anti-sleep
Keep a Mac awake with caffeinate during long builds, downloads, or supervised automation runs.
Agent Browser
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
accli
This skill should be used when interacting with Apple Calendar on macOS. Use it for listing calendars, viewing events, creating/updating/deleting calendar events, and checking availability/free-busy times. Triggers on requests like "check my calendar", "schedule a meeting", "what's on my schedule", "am I free…
agent-browser
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection.
apple-mail
Apple Mail.app integration for macOS. Read inbox, search emails, send emails, reply, and manage messages with fast direct access (no enumeration).