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 agentmods add skills/array-ventures/coworker/messagingnpx skills add Array-Ventures/coworker --skill messaginggit clone --depth 1 https://github.com/Array-Ventures/coworkerWhat 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 | $0.00082 | $0.00781 |
| Opus 5 | $0.00041 | $0.00391 |
| Sonnet 5 | $0.00016 | $0.00156 |
| Haiku 4.5 | $0.00008 | $0.00078 |
Grade A, and why
messaging 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 2d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Messaging
Send messages through connected channels using the msg CLI.
CLI
# Send a DM
msg send --channel whatsapp --to "+1234567890" "Hello!"
# Send to a group (use the group JID)
msg send --channel whatsapp --to "[email protected]" "Daily summary ready."
# Reply to a specific message
msg send --channel whatsapp --to "+1234567890" --reply-to "MSG_ID" "Got it!"
# Send an image with caption
msg send --channel whatsapp --to "+1234567890" --image /path/to/photo.jpg "Check this out"
# Send a document
msg send --channel whatsapp --to "+1234567890" --file /path/to/report.pdf
# Send a voice note
msg send --channel whatsapp --to "+1234567890" --audio /path/to/voice.ogg --ptt
# Send a video with caption
msg send --channel whatsapp --to "+1234567890" --video /path/to/clip.mp4 "Watch this"
# Send a sticker
msg send --channel whatsapp --to "+1234567890" --sticker /path/to/sticker.webp
# List connected channels and their status
msg channels
# List allowlisted WhatsApp groups
msg groups
Media Flags
| Flag | Description |
|---|---|
--image <path> |
Send an image (JPEG, PNG, WebP, GIF) |
--file <path> |
Send a document (PDF, DOCX, etc.) |
--audio <path> |
Send audio (OGG, MP3, M4A) |
--video <path> |
Send video (MP4, MOV) |
--sticker <path> |
Send a sticker (WebP) |
--ptt |
Mark audio as voice note (push-to-talk) |
When using --image, --file, or --video, the text argument becomes the caption.
<no-reply/> Directive
When receiving a group message that does not require a response, output <no-reply/> instead of text. The bridge suppresses sending when this directive is present.
Use <no-reply/> when:
- Message is casual chatter or FYI with no actionable content
- Conversation does not involve you and your input adds no value
- Someone else already answered adequately
Do NOT use <no-reply/> when:
- You are @mentioned — always respond to direct mentions
- You have genuinely useful information to contribute
- Someone asked a question you can answer
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.
- 2d ago First seen · 88 lines · 82 tokens per session scan A b0f74431a9fc
messaging is a skill published in the GitHub repository Array-Ventures/coworker (41 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 82 tokens to every session and 781 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 2026-08-30.
Other skills, from other repositories
seedance
Generate AI videos using Volcengine Seedance model. Supports text-to-video (T2V), image-to-video (I2V), and audio-synced video generation. Use this skill when the user wants to create or generate videos.
music-search
Search cloud drives for downloadable music resources (songs, albums, lossless audio). Use this skill when the user wants to download a specific song or album. Do NOT use for general music information, lyrics, or recommendations.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
claw-link
OpenClaw 实例互联通讯。让不同机器上的 OpenClaw 互发文字/图片/视频消息、发布和分享帖子。每个实例注册一个固定身份（clawid 终身不变，handle/昵称/简介可多轮对话修改）。用户说"给XX的Claw发消息""看看有没有新消息""发个帖子""把这个帖子分享给XX""设置我的Claw身份"时使用。.
qwen-image
Generate images using Qwen Image API (Alibaba Cloud DashScope). Use when users request image generation with Chinese prompts or need high-quality AI-generated images from text descriptions.
video-subtitles
Generate SRT subtitles from video/audio with translation support. Transcribes Chinese (FunASR/Whisper), English (Whisper), Hebrew (ivrit.ai), translates between languages, burns subtitles into video. Use for creating captions, transcripts, or hardcoded subtitles.