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 OpenClaudia/openclaudia-skills --skill wechat-momentsgit clone --depth 1 https://github.com/OpenClaudia/openclaudia-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/openclaudia/openclaudia-skills/wechat-moments)<a href="https://agentmods.dev/skills/openclaudia/openclaudia-skills/wechat-moments"><img src="https://agentmods.dev/badge/skills/openclaudia/openclaudia-skills/wechat-moments/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/openclaudia/openclaudia-skills/wechat-moments"><img src="https://agentmods.dev/badge/skills/openclaudia/openclaudia-skills/wechat-moments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00083 | $0.01098 |
| Opus 5 | $0.00042 | $0.00549 |
| Sonnet 5 | $0.00017 | $0.00220 |
| Haiku 4.5 | $0.00008 | $0.00110 |
Grade A, and why
wechat-moments 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WeChat Moments digest
Turns a WeChat Moments feed into a short ranked digest: what deserves a reply, what is genuinely informative, and what is marketing wearing a personal voice.
The scripts live in a separate repository, not here, because they depend on the WeChat desktop client rather than any marketing API:
https://github.com/OpenClaudia/wechat-moments
git clone https://github.com/OpenClaudia/wechat-moments.git
Read that repo's README before running anything. It documents the setup, the limits, and the risks — this skill is the ranking method, not the plumbing.
Before you touch it
- It does not decrypt anything and never handles keys. It reads a plaintext database that a separate WeChat export tool has already produced. If the user has no export yet, that is step one and it is not this skill's job — the repo lists existing tools for it.
- Moments do not sync in the background. WeChat fetches the timeline only while the Moments window is open. Without a sync the export contains only what the user already scrolled past, so the digest is a replay of what they have already seen. Say so rather than presenting stale posts as today's.
- Tell the user the limits before setting this up on a schedule. It needs WeChat running and logged in, it only stays complete while the machine is awake (sleep gaps are permanently unrecoverable), Tencent may break or patch it at any time, automating the client may be noticed and may carry account risk, and nothing is guaranteed.
- Never post, like, comment, or message on the user's behalf. Reading and writing files is the whole remit.
Ranking
This is the part worth carrying to any feed, not just WeChat.
Score = event weight × relationship weight. Do it yourself from the structured records; do not write a scoring script. The point is judgement — "her mother is in hospital" outranks "went to Kyoto".
Event weight (0-10). Birth, death, serious illness, wedding, divorce, emigration at the top. New job, funding, graduation, a home, a pregnancy just below. Travel and opinions in the middle. Food, gym, weather, scenery at the bottom. Promotion and recruiting score zero.
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 · 95 lines · 83 tokens per session scan A 09ef3425fb34
wechat-moments is a skill published in the GitHub repository OpenClaudia/openclaudia-skills (689 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 1,098 once invoked, about $0.0004 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.