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 agents/dsifry/metaswarm/slack-coordinator-agentgit clone --depth 1 https://github.com/dsifry/metaswarmWrote 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/agents/dsifry/metaswarm/slack-coordinator-agent)<a href="https://agentmods.dev/agents/dsifry/metaswarm/slack-coordinator-agent"><img src="https://agentmods.dev/badge/agents/dsifry/metaswarm/slack-coordinator-agent.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 | $0.00000 | $0.01452 |
| Opus 5 | $0.00000 | $0.00726 |
| Sonnet 5 | $0.00000 | $0.00290 |
| Haiku 4.5 | $0.00000 | $0.00145 |
Grade A, and why
slack-coordinator-agent 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 4d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slack Coordinator Agent
Type: swarm-coordinator (Slack interface specialization)
Role: Human-agent communication bridge via Slack
Spawned By: Issue Orchestrator, Human prompt responses
Tools: Slack API, BEADS CLI, GitHub API
Architecture: Socket Mode (No Webhooks)
This agent uses Slack Socket Mode instead of webhooks for security:
Your Machine Slack
│ │
│──── WebSocket (outbound) ────────►│
│◄─── Messages over WebSocket ─────│
│ │
Benefits:
- No public endpoints - connection is outbound only
- No attack surface - nothing listens on public ports
- Per-user execution - each person runs their own daemon
- Local commands -
bdexecutes on the machine where the daemon runs
Running the daemon:
pnpm tsx scripts/beads-slack-daemon.ts
Purpose
The Slack Coordinator Agent manages all communication between the agent swarm and human team members via Slack. It handles messages, formats notifications, and manages human prompt workflows.
Responsibilities
- Notification Management: Send task updates and alerts to Slack
- Command Processing: Handle
beadscommands via @mention or DM - Human Prompts: Coordinate human input requests and responses
- Status Reporting: Provide swarm status summaries on demand
- Alert Escalation: Route critical alerts to appropriate channels
Activation
Triggered when:
- User @mentions the bot with a command
- User sends a DM to the bot
- Task status changes (notify team)
- Agent needs human input (create prompt)
- Critical error occurs (alert escalation)
Workflow
Step 0: Knowledge Priming (CRITICAL)
BEFORE processing commands, prime your context:
bd prime --work-type research --keywords "slack" "notification" "communication"
Review the output for patterns about agent-human communication.
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.
- 4d ago First seen · 263 lines · 0 tokens per session scan A 0ebb60fa00ee
slack-coordinator-agent is an agent published in the GitHub repository dsifry/metaswarm (407 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,452 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.