swarm

swarm is a command for Claude Code from sifxprime/kodelyth-ecc. It costs 24 tokens per session (818 once invoked), scanned A, original, MIT.

A command that starts several specialist coding agents in parallel, each working in its own isolated Git worktree. A Git worktree is a separate working copy of the same repository.

In plain words
What is it for?
Use it for parallel audits, refactors, incident investigation, security work, or release preparation with selected agent types and launch environments.
Why use it?
It lets multiple agents investigate or work on one task without overwriting one another's files. By default it only shows a plan; execution is optional.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Codex; mentions OpenCode.

Good fit Use it for parallel audits, refactors, incident investigation, security work, or release…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/sifxprime/kodelyth-ecc/swarm
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.

Clone the repo
git clone --depth 1 https://github.com/sifxprime/kodelyth-ecc

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/sifxprime/kodelyth-ecc/swarm.svg)](https://agentmods.dev/commands/sifxprime/kodelyth-ecc/swarm)
Your own site
<a href="https://agentmods.dev/commands/sifxprime/kodelyth-ecc/swarm"><img src="https://agentmods.dev/badge/commands/sifxprime/kodelyth-ecc/swarm.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 818 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00024 $0.00818
Opus 5 $0.00012 $0.00409
Sonnet 5 $0.00005 $0.00164
Haiku 4.5 $0.00002 $0.00082

Measured 3d ago against content hash 6e05f09944c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 3d 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.

commands/swarm.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/swarm

Run a parallel team of ECC specialists on the same task in isolated git worktrees coordinated by a tmux session. The generalized form of /devil-mode, /team-review, /security-audit, and /pre-release — pick any task, pick any agents, get N panes ready to attach.

Quick examples

/swarm audit oauth flow for security regressions
/swarm ship v2.0 --agents release-captain,security-reviewer,e2e-runner --execute
/swarm refactor payments module --agents 6 --harness codex --execute
/swarm production is down, auth service 502s --agents incident-commander,debug-detective,silent-failure-hunter --execute

Behavior

By default, prints the dry-run plan (safe to inspect). Add --execute to actually create worktrees, spawn the tmux session, and launch agents.

Flag Effect
--task "..." Required (or use --plan plan.json).
--agents N Smart-pick N specialists from task signals + baseline anchors + rotation.
--agents name1,name2,... Explicit agent list.
--harness claude|codex|opencode|windsurf|echo Launcher template (default claude).
--seed <path> Overlay path from main repo into each worktree (e.g. --seed .env).
--base-ref <ref> Branch base for all worktrees (default HEAD).
--session <name> Override the auto-generated tmux session name.
--replace Tear down any existing session/worktrees with the same names.
--execute Create worktrees + tmux + launch agents.
--write-only Just write coordination files without spawning.
--json Print the full plan as JSON.

Smart agent picking

If you pass --agents N (a number), the swarm picks specialists in this order:

  1. Signal-driven — task keywords match specialist (security → security-reviewer, perf → performance-optimizer, API → api-guardian, …).
  2. Baseline anchorscode-reviewer + pair-programmer get added (every task benefits).
  3. Rotation fill — 4/6/8-agent default rotations tuned for breadth.

Read the full file on GitHub · 69 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. 3d ago First seen · 69 lines · 24 tokens per session scan A 6e05f09944c8

Subscribe to this mod's changes

swarm is a command published in the GitHub repository sifxprime/kodelyth-ecc (11 stars, last pushed 4d ago), licensed MIT. It adds 24 tokens to every session and 818 once invoked, about $0.0001 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 2026-09-03.

Related

Other commands, from other repositories

pr

Create a clear, reviewer-friendly pull request for the committed work on the current branch. The PR itself is the artifact — produce no separate report. You never modify source files; your writes are git push and the PR. Every fact belongs in the PR title and body.

coleam00/Archon · 0 tokens

sync-pr-body

Bring the pull request description back in line with the code after correction rounds changed it. The description was written when the draft PR opened; corrections since then may have falsified specific claims in it. Your product is an accurate PR body — nothing else.

coleam00/Archon · 0 tokens

worktree-cleanup

A command for removing a Git worktree, which is a separate working folder linked to the same repository, after its pull request is merged.

sangrokjung/claude-forge · 12 tokens

refactor-workflow.template

This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.

evan043/claude-cli-advanced-starter-pack · 0 tokens

ship

Encodes the "stage and commit" ritual: verify (receipt gate) → scope → branch → write the commit message from what is actually staged → commit → push → open PR to the default branch → move the Jira issue to In Review. NO merge (merging is the reviewer's call). NO tag (deploys are project-specific and out of scope).

shashankreddy509/claude-tdd-kit · 0 tokens

start-feature

Jalankan AI Agents Rogue end-to-end untuk permintaan user di chat ini (override mode ke e2e untuk tugas ini).

rogue-dev-studio/ai-agents-rogue · 0 tokens