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 sttts/slagent --skill slaudegit clone --depth 1 https://github.com/sttts/slagentWrote 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/sttts/slagent/slaude)<a href="https://agentmods.dev/skills/sttts/slagent/slaude"><img src="https://agentmods.dev/badge/skills/sttts/slagent/slaude/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/sttts/slagent/slaude"><img src="https://agentmods.dev/badge/skills/sttts/slagent/slaude.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 | $0.00000 | $0.02434 |
| Opus 5.5 | $0.00000 | $0.00974 |
| Sonnet 5.5 | $0.00000 | $0.00487 |
| Haiku 4.5 | $0.00000 | $0.00243 |
Grade A, and why
slaude 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: slaude — Slack-Mirrored Claude Code Sessions
When to Use
Use this skill when asked to start, stop, join, or manage Claude Code sessions mirrored to Slack via slaude. Typical triggers:
- "Start a Claude session in #channel"
- "Mirror this to Slack"
- "Join that Slack thread with a new agent"
- "Resume the session"
- "Stop/quit the session"
- "Kill this session" / "End the session" / "Stop yourself"
- "List running sessions" / "What sessions are active"
Prerequisites
slaudebinary must be installed and in PATH (or built locally from the slagent repo)- Slack credentials configured via
slaude auth - Target Slack channel must be accessible to the authenticated user
Verify setup:
slaude status
slaude version # check installed version
The version is also injected into the agent's system prompt.
Starting a Session
Start a new Claude Code session mirrored to a Slack thread:
slaude start #channel "your prompt here"
slaude start https://team.slack.com/archives/C123 "your prompt here"
slaude start @user "your prompt here"
Key flags:
| Flag | Description |
|---|---|
[target] |
Positional: Slack URL, #channel, @user, or channel ID |
--locked |
Lock to owner only (default for start) |
--observe |
Observe mode: read all messages, only respond to authorized users |
--open |
Open for all thread participants |
--debug |
Write raw JSON events for troubleshooting |
--no-bye |
Skip goodbye message on exit |
--dangerous-auto-approve green |
Auto-approve read-only operations (overrides classifier.yaml) |
--dangerous-auto-approve yellow |
Auto-approve local writes too (overrides classifier.yaml) |
--dangerous-auto-approve-network known |
Auto-approve network to known hosts (overrides classifier.yaml) |
--dangerous-auto-approve-network any |
Auto-approve all network access (overrides classifier.yaml) |
Access mode flags (--locked, --observe, --open) are mutually exclusive.
When no flag is given — interactive terminal prompts Closed, oBserve, or open? [cBo]; non-interactive: start defaults to --locked, join/resume default to --observe.
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 · 264 lines · 0 tokens per session scan A 5e2fc6bc1cb9
slaude is a skill published in the GitHub repository sttts/slagent (22 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,434 tokens. 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
remindme
⏰ simple Telegram reminders for OpenClaw. cron, zero dependencies.
slackcli
Read, send, search, and manage Slack workspaces with the slackcli binary. Installs slackcli if missing and checks or proposes authentication first. Use whenever the user mentions Slack or pastes a slack.com link.
slack-messaging
Use when writing, drafting, scheduling, or improving a Slack message, announcement, or reply sent via the Slack MCP tools (slacksendmessage, slacksendmessagedraft, slackschedulemessage). Covers Slack markdown formatting, message structure, thread etiquette, reactions, and scheduling, and points to the right dialect…
slack-tool
Slack integration tool. It handles message sending and receiving, search, checking unreplied messages, channel list, and emoji reactions. Use when: Use when: you need to post to Slack, view the channel list, reply in threads, check unreplied messages, or add reactions.
workflow-builder
Use when building and automating business workflows with Notion task tracking, Slack notifications, Kanban boards, and cross-functional process orchestration.
slack-webhook
Send the user a Slack message as Claude — progress, a finished task, an alert, anything worth interrupting them for. Use whenever you want to reach the user outside this chat. Required instead of the Slack connector, which posts as the user and doesn't notify them.