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/0xranx/golembot/message-pushnpx skills add 0xranx/golembot --skill message-pushgit clone --depth 1 https://github.com/0xranx/golembotWrote 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/0xranx/golembot/message-push)<a href="https://agentmods.dev/skills/0xranx/golembot/message-push"><img src="https://agentmods.dev/badge/skills/0xranx/golembot/message-push.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.00960 |
| Opus 5 | $0.00028 | $0.00480 |
| Sonnet 5 | $0.00011 | $0.00192 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
message-push scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://localhost:$PORT/api/send \ How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Message Push
You can send messages to IM channels proactively -- to groups or individual users -- without waiting for an incoming message.
Recognizing Push Intent
Note: if the user asks you to send a FILE or IMAGE (e.g. a generated document, chart, photo), do NOT use this skill — instead save to temp_file/ and emit [SEND_IMAGE: ...] / [SEND_FILE: ...] markers (see the im-adapter skill). This skill only sends TEXT messages.
Watch for phrases like:
- "send this to the ops group"
- "tell Alice in DM that..."
- "post this summary to #general"
- "notify the team on Feishu"
- "forward this to chat oc_xxx"
Sending Workflow
Follow these steps when the user requests a message push:
- Identify the target -- determine the channel name and chatId from the user's request
- Discover available channels -- call
GET /api/channelsto confirm the channel exists and supports sending - Compose the message -- draft the text content, following im-adapter formatting guidelines
- Confirm with the user -- if this is the first time sending to this chat, show the draft and ask for approval
- Send the message -- call
POST /api/sendwith the channel, chatId, and text - Report the result -- tell the user whether the send succeeded or failed
Send API
curl -X POST http://localhost:$PORT/api/send \
-H "Content-Type: application/json" \
-d '{
"channel": "feishu",
"chatId": "oc_xxxx",
"text": "Hello from the bot!"
}'
Request Fields
| Field | Type | Required | Description |
|---|---|---|---|
channel |
string | yes | Channel name: feishu, dingtalk, wecom, slack, telegram, discord |
chatId |
string | yes | Chat/group/conversation ID on the target platform |
text |
string | yes | Message content (Markdown supported) |
Response
200 { "ok": true }-- message sent successfully404-- channel not found (check available channels)501-- channel does not support proactive send503-- no channel adapters available
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.
- 5d ago First seen · 105 lines · 55 tokens per session scan A 783ca977a9c7
message-push is a skill published in the GitHub repository 0xranx/golembot (320 stars, last pushed 17d ago), licensed MIT. It adds 55 tokens to every session and 960 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
give-me-tips
Explains any senpi tip in depth, including Tip: lines in the TUI. Use when the user asks about a tip, what a tipped feature does, or which tips they can see.
cursor-delegate
Delegate bounded light-to-medium implementation, investigation, documentation, configuration, testing, and tooling work to Cursor Bridge after the primary agent owns direction and risk boundaries. Also use when the user explicitly asks to create, keep, continue, inspect, or close the same Cursor execution session…
recap
Produce a weekly/date-range recap from emails, Slack, Jira/Confluence, and vault notes. Args: [dates]. Default = this week.
followup-todos
Extract action items as plain markdown bullets (with confirmation). Args: . No args = run /note-status pending --step=todos.
meeting
Create or wrap meeting notes. Args: {title} [folder=X], wrap , wrap pending [today|this week|dates]. No args = pick from Google Calendar.
organize-meetings
Triage Meetings/inbox/ — move each file to the correct subfolder by finding adjacent/similar notes via qmd, applying learned routing conventions from memory, and confirming with the user.