agentmods.dev

weilink

weilink is a skill for Claude Code, Codex from Oaklight/weilink. It costs 46 tokens per session (777 once invoked), scanned A, original, MIT.

A skill for managing WeChat conversations through WeiLink, including messages, media, and bot sessions. WeChat is a messaging platform, and a bot session is its connected account context.

In plain words
What is it for?
Use it to poll or search message history, send text or files, download media, log in or out, and manage sessions.
Why use it?
It provides defined actions for checking conversations and communicating with contacts from Claude Code.

Skill for Claude CodeCodex

Part of the weilink plugin — 1 skill, 1 hook, 1 MCP server shipped together

not rated 17 1mo ago A scan 46 tokens original MIT
View the source file Oaklight/weilink
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.

agentmods
npx agentmods add skills/oaklight/weilink/weilink
Any agent
npx skills add Oaklight/weilink --skill weilink
Clone the repo
git clone --depth 1 https://github.com/Oaklight/weilink

Made for: Claude Code, Codex.

Or install weilink, the plugin that ships this one along with the rest of its 1 skill, 1 hook, 1 MCP server.

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 weilink

README.md
[![agentmods](https://agentmods.dev/badge/skills/oaklight/weilink/weilink.svg)](https://agentmods.dev/skills/oaklight/weilink/weilink)
Your own site
<a href="https://agentmods.dev/skills/oaklight/weilink/weilink"><img src="https://agentmods.dev/badge/skills/oaklight/weilink/weilink.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 777 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00046 $0.00777
Opus 5 $0.00023 $0.00388
Sonnet 5 $0.00009 $0.00155
Haiku 4.5 $0.00005 $0.00078

Measured 4d ago against content hash 4ace7c55ed4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

weilink 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 4d 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.

src/weilink/integrations/claude_code/skills/weilink/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Arguments: $ARGUMENTS

Available MCP Tools

Messaging

  • recv — Poll for new messages (timeout configurable, default 5s)
  • send — Send text, image, file, video, or voice to a WeChat user
  • download — Download media from a received message by message_id
  • history — Query past messages with filters (user, type, direction, time range, text search)

Session Management

  • sessions — List all bot sessions and connection status
  • login — Start QR code login for a new or existing session
  • logout — Disconnect a session
  • rename_session — Rename a bot session
  • set_default — Set the default session

Quick Workflows

Check new messages

New messages are automatically injected into context when the user submits a prompt. For explicit polling, use recv or history with a since filter.

Reply to someone

  1. Get the user ID from a received message (from_user field, format: [email protected])
  2. Use send with to=<user_id> and text=<reply>

Search message history

Use history with filters:

  • user_id — filter by contact
  • text_contains — full-text search
  • since / until — time range (ISO 8601 or unix ms)
  • direction — "received" or "sent"
  • msg_type — TEXT, IMAGE, VOICE, FILE, VIDEO

Send media

Use send with the appropriate path parameter:

  • image_path — send an image
  • file_path + file_name — send a file
  • video_path — send a video
  • voice_path — send a voice message

Download received media

Use download with the message_id from a received message. Files are saved to ~/.weilink/downloads/ by default (override with save_dir).

Important Notes

  • Message quota: Each context_token allows 10 outbound messages. After that, wait for the user to send a new inbound message.
  • Text limit: Messages must be <= 16 KiB UTF-8. Split longer content.
  • Session: When multiple sessions exist, send auto-routes to the session holding a valid context_token for the target user.
  • Login: Run login to scan a QR code. One WeChat account can only bind to one bot at a time.

Read the full file on GitHub · 74 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.

  1. 4d ago First seen · 74 lines · 46 tokens per session scan A 4ace7c55ed4a

Subscribe to this mod's changes

weilink is a skill published in the GitHub repository Oaklight/weilink (17 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 777 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 2026-08-30.

ai-agentbotchatbotilinksdk
Related

Other skills, from other repositories

agents-sdk-dotnet-activityhandler-migration

Use when migrating a Microsoft 365 Agents SDK agent that uses ActivityHandler or TeamsActivityHandler to AgentApplication. This is ONLY for DotNet projects that uses Microsoft.Agents. packages. Triggered by Agents SDK bots that subclass ActivityHandler or TeamsActivityHandler that need to be modernized to…

microsoft/Agents · 76 tokens

agents-sdk-typescript

Use when any code imports @microsoft/agents-hosting, @microsoft/agents-hosting-express, or related Agents SDK packages, or when the user is building, configuring, or asking questions about a Microsoft 365 Agents SDK agent in TypeScript. Trigger on questions about environment variables, connection configuration…

microsoft/Agents · 111 tokens

agents-sdk-dotnet

Use when any code imports Microsoft.Agents.Hosting.AspNetCore, Microsoft.Agents.Builder, or related Agents SDK packages, or when the user is building, configuring, or asking questions about a Microsoft 365 Agents SDK agent in C# / .NET. Trigger on questions about appsettings.json, connection configuration…

microsoft/Agents · 112 tokens

agents-sdk-python-otel

Use when adding, configuring, validating, or troubleshooting OpenTelemetry observability for a Microsoft 365 Agents SDK application in Python. Trigger when the user mentions OpenTelemetry, OTel, telemetry, traces, metrics, logs, OTLP, Aspire Dashboard, Application Insights, Azure Monitor, distributed tracing, custom…

microsoft/Agents · 81 tokens

agents-sdk-provision

Use when provisioning Azure resources for a Microsoft Agents SDK application — including creating an Azure Bot Service resource, setting up Entra app registrations, configuring identity credentials (UserManagedIdentity, FederatedCredentials, or ClientSecret), adding a Teams channel, running Bicep deployments for SSO…

microsoft/Agents · 131 tokens

agents-sdk-typescript-otel

Use when adding, configuring, validating, or troubleshooting OpenTelemetry observability for a Microsoft 365 Agents SDK application in JavaScript or TypeScript. Trigger when the user mentions OpenTelemetry, OTel, telemetry, traces, metrics, logs, OTLP, Aspire Dashboard, Application Insights, Azure Monitor, distributed…

microsoft/Agents · 88 tokens