A host skill that copies selected WeChat desktop chats into JSON, can create an optional language-model report, and answers questions about the captured messages. WeChat must run on the same computer as the OpenClaw Gateway.

Monitoring chosen WeChat groups, exporting their messages, generating reports, and querying the captured conversations.

It turns messages in selected desktop chats into files that an AI agent can search, summarize, and use for questions.

weclaw — Skill for Claude Code and Codex by Numaira-Technology

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/Numaira-Technology/weclaw-cua

agentmods

npx agentmods add skills/numaira-technology/weclaw-cua/weclaw

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/numaira-technology/weclaw-cua/weclaw/github.svg)](https://agentmods.dev/skills/numaira-technology/weclaw-cua/weclaw)

Your own site

<a href="https://agentmods.dev/skills/numaira-technology/weclaw-cua/weclaw"><img src="https://agentmods.dev/badge/skills/numaira-technology/weclaw-cua/weclaw/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/numaira-technology/weclaw-cua/weclaw"><img src="https://agentmods.dev/badge/skills/numaira-technology/weclaw-cua/weclaw.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,040 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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 Agent Snooping · line 43
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00031	$0.01040
Opus 5.5	$0.00012	$0.00416
Sonnet 5.5	$0.00006	$0.00208
Haiku 4.5	$0.00003	$0.00104

Measured 1mo ago against content hash ad6bf532e601, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

weclaw 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 1mo 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.

openclaw_skill/weclaw/SKILL.md · 95 lines

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.

WeClaw (OpenClaw host skill)

WeChat must be the desktop app on the same machine as OpenClaw Gateway. This skill automates the UI; it does not work from a phone alone.

One-time setup on the host

Clone WeClaw next to your workspace or any fixed path. Set a durable env var (shell profile or OpenClaw skills.entries.weclaw.env):
- WECLAW_ROOT = absolute path to the WeClaw git checkout (directory that contains run.sh).

Python venv (from WeClaw README):

cd "$WECLAW_ROOT"
python3 -m venv .venv
./.venv/bin/pip install -r requirements.txt

Copy config/config.json.example to config/config.json. Fill groups_to_monitor and either put openrouter_api_key in the file or export OPENROUTER_API_KEY (env overrides JSON when present per WeClaw config).
macOS: grant Accessibility to the app running Python (Terminal, iTerm, or the OpenClaw host). Windows: match elevation with WeChat if needed.
Install this skill into the active OpenClaw workspace skills/weclaw/ (the script uses openclaw skills list --json to find workspaceDir when openclaw is on PATH, or set OPENCLAW_WORKSPACE to override):
```
"$WECLAW_ROOT/scripts/install_openclaw_skill.sh"
```
Or copy {baseDir} (this skill’s directory) into your workspace skills/weclaw/ yourself. OpenClaw discovers skills/weclaw/SKILL.md.

Optional openclaw.json (JSON5) snippet so the agent always sees WECLAW_ROOT:

skills.entries.weclaw.env.WECLAW_ROOT = "/absolute/path/to/weclaw"

Run the capture + report pipeline

From the host shell (or schedule via OpenClaw cron / systemd / launchd calling the same command):

export WECLAW_ROOT="/absolute/path/to/weclaw"
export WECLAW_CONFIG_PATH="$WECLAW_ROOT/config/config.json"
cd "$WECLAW_ROOT"
./run.sh

With a non-default config path:

./run.sh /path/to/other-config.json

Stdout is the generated report text (or No matching messages found.). Structured chat exports are JSON files under output_dir from config (default output/).

Read the full file on GitHub · 95 lines

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.

1mo ago First seen · 95 lines · 31 tokens per session scan A ad6bf532e601

Subscribe to this mod's changes

weclaw is a skill published in the GitHub repository Numaira-Technology/weclaw-cua (34 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,040 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

Productivity

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…

nexu-io/open-design · 117 tokens

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.

paperclipai/paperclip · 30 tokens

rowboat-spaces

How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.

rowboatlabs/rowboat · 60 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

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.

pinchtab/pinchtab · 52 tokens

mochi-remind

Handle due reminders — notify the user with natural language and mark them done.

kirodotdev/KiroCrew · 20 tokens