swarm

swarm is a command for Claude Code from liortesta/ClawdAgent. It costs 0 tokens per session (947 once invoked), scanned A, original, Apache-2.0.

A command for coordinating several coding agents on one larger task. It can split work into independent parts, assign priorities, track progress on a shared task board, and use leader-worker, ensemble, or sequential workflows.

In plain words
What is it for?
Use it for multi-part implementation, independent debugging or reviews, and pipelines such as design, implementation, testing, and review.
Why use it?
It organizes parallel or staged work so multiple agents can contribute while their results are coordinated and reviewed.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/liortesta/clawdagent/swarm
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

Made for: Claude Code.

Wrote 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.

agentmods badge for swarm

README.md
[![agentmods](https://agentmods.dev/badge/commands/liortesta/clawdagent/swarm.svg)](https://agentmods.dev/commands/liortesta/clawdagent/swarm)
Your own site
<a href="https://agentmods.dev/commands/liortesta/clawdagent/swarm"><img src="https://agentmods.dev/badge/commands/liortesta/clawdagent/swarm.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 947 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00947
Opus 5 $0.00000 $0.00474
Sonnet 5 $0.00000 $0.00189
Haiku 4.5 $0.00000 $0.00095

Measured 4d ago against content hash 36937aa78a4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

swarm 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.

.claude/commands/swarm.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Swarm Mode — Coordinated Agent Team

Launch a coordinated multi-agent team with a shared task board and Leader→Workers pattern.

Process:

1. Task Analysis

  • Break the task into independent, parallelizable sub-tasks
  • Identify dependencies between sub-tasks
  • Assign each sub-task a priority (P0=blocker, P1=critical, P2=normal)

2. Team Assembly

Choose the right team pattern:

Leader→Workers (default):

  • 1 Leader agent (CTO or Architect) coordinates
  • 2-5 Worker agents execute in parallel
  • Leader reviews all output before merging

Ensemble (for review/debugging):

  • 3-5 agents work on the SAME problem independently
  • Compare results, pick best or synthesize

Pipeline (for sequential work):

  • Each agent handles one stage, passes output to next
  • Stage 1: Design → Stage 2: Implement → Stage 3: Test → Stage 4: Review

3. Task Board

Create a shared task board:

## SWARM TASK BOARD
| # | Task | Assignee | Status | Branch | Depends On |
|---|------|----------|--------|--------|-----------|
| 1 | ... | agent-1 | pending | feat/task-1 | - |
| 2 | ... | agent-2 | pending | feat/task-2 | - |
| 3 | ... | agent-3 | pending | feat/task-3 | 1,2 |

4. Execution

  • Spawn agents in parallel using subagents or agent teams
  • Each agent works in its own git branch (or worktree if available)
  • Use @mentions to request help: "@security-auditor review this auth logic"
  • Leader monitors progress and resolves conflicts

5. Integration

  • Leader reviews all completed tasks
  • Merge branches in dependency order
  • Run /ship to verify everything works together
  • Resolve any integration conflicts

Team Templates:

Full Stack Feature

Leader: CTO
Workers:
  - architect → API design + DB schema
  - dev-backend → API implementation
  - dev-frontend → UI implementation
  - qa-engineer → Tests for all layers
  - security-auditor → Real-time audit

Bug Investigation

Pattern: Ensemble (3 investigators)
  - Agent A: Top-down (start from error, trace back)
  - Agent B: Bottom-up (start from data, trace forward)
  - Agent C: Bisect (git bisect to find breaking commit)
  → Compare findings, identify root cause

Read the full file on GitHub · 127 lines

Changes

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.

  1. 4d ago First seen · 127 lines · 0 tokens per session scan A 36937aa78a4e

Subscribe to this mod's changes

swarm is a command published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 7d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 947 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.