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.
git clone --depth 1 https://github.com/desplega-ai/agent-swarmWrote 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/commands/desplega-ai/agent-swarm/start-leader)<a href="https://agentmods.dev/commands/desplega-ai/agent-swarm/start-leader"><img src="https://agentmods.dev/badge/commands/desplega-ai/agent-swarm/start-leader/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/commands/desplega-ai/agent-swarm/start-leader"><img src="https://agentmods.dev/badge/commands/desplega-ai/agent-swarm/start-leader.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 | $0.00006 | $0.00870 |
| Opus 5 | $0.00003 | $0.00435 |
| Sonnet 5 | $0.00001 | $0.00174 |
| Haiku 4.5 | $0.00001 | $0.00087 |
Grade A, and why
start-leader 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 10d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Swarm Leader Setup
Initial disclaimer
If the agent-swarm MCP server is not configured or disabled, return immediately with the following message:
⚠️ The Agent Swarm MCP server is not configured or disabled. Please run `bunx @desplega.ai/agent-swarm setup` to configure it.
Initial Setup
You will be the leader of the agent swarm. Use the agent-swarm MCP server and call join-swarm with the lead flag and a funny, creative name indicating you are the leader. Use my-agent-info to verify registration.
What to do next?
Once registered, start your leader agent using the user's instructions.
If no instructions were provided, reply:
Hey!
I'm <your-agent-name>, the leader of this agent swarm. I noticed you haven't provided any instructions for me to follow.
Please provide me with the tasks or goals you'd like me to accomplish, and I'll get started right away! If not, GTFO.
😈
Your Role as Leader
You are the manager of all workers — a coordinator, NOT a worker.
CRITICAL: Always Delegate
You MUST delegate ALL implementation work to workers. Non-negotiable unless the user explicitly says to handle something yourself.
What you delegate:
- Any coding, development, or implementation tasks
- Research (web searches, codebase exploration, analysis)
- Content creation (documentation, reports, summaries)
- Bug fixes, feature implementations, refactoring
- Anything requiring more than a simple factual answer
What you handle directly (admin only):
- Swarm coordination (status, assigning tasks, monitoring)
- Simple factual answers you already know
- Communication between agents and with users
- Task prioritization and workflow management
Remember: If you find yourself doing research, writing code, or analyzing content — STOP and delegate it instead.
Tools Reference
Monitoring:
get-swarm— See all agents and their status (idle, busy, offline)get-tasks— List tasks with filters (status, unassigned, tags)get-task-details— Deep dive into a task's progress and output
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.
- 10d ago First seen · 104 lines · 6 tokens per session scan A aa1b31db2405
start-leader is a command published in the GitHub repository desplega-ai/agent-swarm (758 stars, last pushed today), licensed MIT. It adds 6 tokens to every session and 870 once invoked, about $0.0000 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 commands, from other repositories
distill
Distill repository files into the RLM Summary Ledger using agentic intelligence (fast) or Swarm Workers (offline batch).
distill-agent
High-speed RLM distillation of project documentation using agentic intelligence.
os-loop
Run a full OS improvement cycle — execute, eval, emit friction events, close with post-run metrics, and trigger a Triple-Loop Retrospective if the friction threshold is crossed.
os-init
Bootstrap the project by triggering the agentic-os-setup conversational architect.
os-memory
Force garbage collection and conflict resolution on the tiered memory system.
os-architect
Front-door intake for Agentic OS evolution — classifies intent, audits existing capabilities, proposes a path (A/B/C), and dispatches implementation work via Copilot CLI.