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 opensquad-ai/opensquad --skill external-im-integrationgit clone --depth 1 https://github.com/opensquad-ai/opensquadWrote 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/opensquad-ai/opensquad/external-im-integration)<a href="https://agentmods.dev/skills/opensquad-ai/opensquad/external-im-integration"><img src="https://agentmods.dev/badge/skills/opensquad-ai/opensquad/external-im-integration/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/opensquad-ai/opensquad/external-im-integration"><img src="https://agentmods.dev/badge/skills/opensquad-ai/opensquad/external-im-integration.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 | $0.00050 | $0.01681 |
| Opus 5.5 | $0.00020 | $0.00672 |
| Sonnet 5.5 | $0.00010 | $0.00336 |
| Haiku 4.5 | $0.00005 | $0.00168 |
Grade A, and why
external-im-integration 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.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Enable agents to send and receive messages from external IM platforms. After setup, the agent can:
- Receive group chat and direct messages from external IM
- Reply to incoming messages
- Proactively send messages to groups or users
Architecture (read this first for troubleshooting)
The message flow for all external IM platforms is the same:
External IM (Feishu/QQ/Telegram) → Platform WebSocket/Webhook
→ Platform Adapter Process (listens for incoming events)
→ POST http://127.0.0.1:9700/api/chat
→ External API Adapter Process (relay layer)
→ Gateway WebSocket → Agent
Each platform needs TWO separate processes managed by the Launcher:
- Platform adapter (e.g.,
plugins.feishu.adapter) — listens for incoming messages from the IM platform - External API adapter (
plugins.external_api.adapter, port 9700) — shared relay that forwards to Gateway
These are not in-process plugins — they are subprocesses spawned by the Launcher via the service field in plugin.json.
Prerequisites
- An app on the target IM platform's developer console (Feishu Open Platform, Telegram BotFather)
- Launcher running (manages adapter processes)
pip install lark-oapifor Feishu, or respective SDK for Telegram
Step-by-Step Guide (Feishu Example)
Step 1: Verify service field in both plugin.json files
This step is mandatory — without the service field, Launcher won't start the adapter processes.
plugins/external_api/plugin.json (shared by all platforms):
"service": {
"cmd": "python -m plugins.external_api.adapter",
"default_port": 9700,
"health_check": "/api/health",
"startup_timeout": 30,
"auto_start": true
}
plugins/feishu/plugin.json (or plugins/telegram/plugin.json):
"service": {
"cmd": "python -m plugins.feishu.adapter",
"auto_start": true,
"startup_timeout": 30
}
⚠️ Note — PluginManager uses a merge strategy that preserves the service field when updating plugin.json. If service is null (older versions may have overwritten it), re-write it manually and restart Launcher.
What ships with it
1 file 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.
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 · 185 lines · 50 tokens per session scan A b7ede83ba6ae
external-im-integration is a skill published in the GitHub repository opensquad-ai/opensquad (6 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,681 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
background-task
Add or modify work that runs outside the request/response cycle — emails, document ingestion, webhooks, cleanups, scheduled jobs. Use when something is slow or fire-and-forget, or when adding a periodic/cron task. This project's queue is {{ cookiecutter.backgroundtasks }}.
channel-bot
Work with messaging-channel bots (Telegram / Slack) — register a bot, route inbound messages through the AI agent, handle webhooks vs polling, or add a new channel adapter. Use when wiring chat into a messaging platform or debugging bot delivery.
mcp_protocol
A set of rules and a Python structure for wrapping a service so AI clients can call its tools through MCP, an open protocol for connecting models to external tools. It uses server-sent events over HTTP for communication.
http_request
Make HTTP requests (GET, POST, PUT, DELETE, PATCH) to any API endpoint. Use when: the user asks to call an API, test an endpoint, fetch JSON/data from a URL, or interact with a REST API. NOT for: web scraping (use webscraper), web search (use tavilysearch), or file downloads (use curl/wget).
code_analysis_patterns
Rules for analysing Python projects and identifying functions that could become MCP tools, which are callable functions exposed to an AI system.
gitlab_write
Create, modify resources in GitLab. Use gitlabapi for everything.