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 tomzx/agents --skill post-slack-messagegit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/post-slack-message)<a href="https://agentmods.dev/skills/tomzx/agents/post-slack-message"><img src="https://agentmods.dev/badge/skills/tomzx/agents/post-slack-message/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/tomzx/agents/post-slack-message"><img src="https://agentmods.dev/badge/skills/tomzx/agents/post-slack-message.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00083 | $0.01932 |
| Opus 5.5 | $0.00033 | $0.00773 |
| Sonnet 5.5 | $0.00017 | $0.00386 |
| Haiku 4.5 | $0.00008 | $0.00193 |
Grade A, and why
post-slack-message 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 today.
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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Post Slack Message
Posts a message to a Slack channel or as a thread reply using post_slack_message.py (Slack Web API chat.postMessage).
This skill contains the compose-and-confirm flow so it can use the question tool; the script is the send primitive.
Behavior modes
- Review mode (default): write the message to a temp file, then use the question tool to ask the user to confirm sending the content of that file. Nothing is posted until the user approves.
- Immediate mode (
--yes): skip the confirmation and post right away. Use this for fully unattended flows (scheduled jobs, automation, or a caller that has already shown the message to the user).
--yes (also -y, --send, --auto) is accepted in any position of the arguments.
Prerequisites
SLACK_TOKENset. A bot token (xoxb-) only needs the token; a web/browser token (xoxc-) also needsSLACK_COOKIE(thexoxd-value), the same credentials used byslack-kb-individualandslackx. Place them in.envat the repo root or export them in the environment.- The target channel: a channel id, a Slack archive URL, or a channel name.
- Apply the shared communication guidelines in
skills/communication-guidelines/SKILL.mdwhen composing the message.
Inputs
- channel: one of
--channel <id>,--channel-url <url>, or--channel-name <name>(the name is resolved to an id viaconversations.list). Exactly one is required. - thread_ts: optional
--thread-ts <ts>to post as a thread reply; auto-detected when--channel-urlpoints at a thread message. - message: the message body in Slack mrkdwn (
*bold*,<@USERID>mentions,<https://url|label>links). Provided as a trailing argument, via--file <path>, or via--stdin. Exactly one source. If the draft was written in regular markdown (the copy/paste convention), convert it to Slack mrkdwn before sending. - mode:
--yesfor immediate send; otherwise review mode. - dry-run:
--dry-runresolves the channel and shows what would be posted without sending. Use it to pre-validate credentials and targeting.
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.
- today Changed · +1 lines d912cbe39f93
- 22d ago Changed · +23 lines 71b8561736a3
- 24d ago Changed 02a568fc4573
- 28d ago Changed · +1 lines 2ac6ca81efb2
- 1mo ago Changed 430bba500d03
- 1mo ago Changed b8c5a9820b9a
- 1mo ago First seen · 146 lines · 83 tokens per session scan A 6ef4ab47c2b7
post-slack-message is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 1,932 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
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…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
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.
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.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.