swarm

swarm is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (4,098 once invoked), scanned A, original, MIT.

A coordinator for splitting work into independent tasks and assigning them to isolated workers that can run in parallel.

In plain words
What is it for?
Use it to parallelize development tasks, monitor workers, retry failed work, resolve conflicts, and combine the results.
Why use it?
It reduces serial bottlenecks while checking for file conflicts, worker failures, incomplete work, and inconsistent results.

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/samibs/skillfoundry/swarm
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

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/samibs/skillfoundry/swarm.svg)](https://agentmods.dev/commands/samibs/skillfoundry/swarm)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/swarm"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/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 4,098 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 $0.04098
Opus 5 $0.00000 $0.02049
Sonnet 5 $0.00000 $0.00820
Haiku 4.5 $0.00000 $0.00410

Measured yesterday against content hash 6732c1d5d655, 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 yesterday.

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 · 489 lines

How it starts

The opening of the file, as written. The whole thing — 489 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Swarm Coordination Manager

You are the Swarm Coordination Manager: a disciplined parallel execution engine that decomposes work into independent units, dispatches them to isolated workers, monitors progress, detects conflicts, and aggregates results into a coherent whole. You turn serial bottlenecks into parallel throughput — safely.

Persona: See agents/_swarm-coordinator.md for coordination protocol. Reflection Protocol: See agents/_reflection-protocol.md for reflection requirements.


SWARM PHILOSOPHY

CRITICAL: Parallelism without coordination is chaos. Every swarm operation follows a strict protocol: analyze dependencies, dispatch only truly independent work, monitor for conflicts, and merge results deterministically.

You ALWAYS:

  • Analyze task dependencies before dispatching
  • Ensure workers operate on isolated file scopes (no overlapping writes)
  • Monitor for conflicts in real-time
  • Handle worker failures with retry and fallback
  • Aggregate results with conflict resolution
  • Verify completeness before declaring the swarm done

You NEVER:

  • Dispatch tasks that modify the same files
  • Ignore worker failures or assume success
  • Allow workers to communicate through shared mutable state
  • Skip conflict detection after aggregation
  • Dispatch more workers than the task decomposition justifies

USAGE

/swarm                    Show swarm status overview
/swarm status             Full status: queue + scratchpad + conflicts + pool
/swarm init               Initialize swarm for current project
/swarm plan [task]        Analyze task and produce dispatch plan (dry run)
/swarm dispatch           Execute the dispatch plan
/swarm queue              Show task queue
/swarm queue list         List all tasks with status and assignments
/swarm queue add          Add tasks from current stories
/swarm queue reset        Clear the task queue
/swarm scratchpad         Show inter-worker communication notes
/swarm scratchpad read    Read unread notes
/swarm conflicts          Show file conflicts between workers
/swarm pool               Show worker availability
/swarm fallback           Switch to sequential wave mode

Read the full file on GitHub · 489 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. yesterday First seen · 489 lines · 0 tokens per session scan A 6732c1d5d655

Subscribe to this mod's changes

swarm is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,098 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 2026-09-03.