run-swarm

run-swarm is a skill for Claude Code, Codex from Zate/cc-plugins. It costs 17 tokens per session (1,797 once invoked), scanned A, original, MIT.

An automated workflow that assigns development-plan tasks to fresh-context coding agents, meaning agents that start each task with a clean working context. It coordinates their work and checks whether each phase is complete.

In plain words
What is it for?
Use it to execute multi-step development plans through several coordinated agents and validate the resulting work.
Why use it?
It helps divide a larger plan into separate tasks and reduces the amount of context one agent must hold at once. The workflow also validates completed phases with tests or builds.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the devloop plugin — 19 skills, 6 agents shipped together

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 skills/zate/cc-plugins/run-swarm
Any agent
npx skills add Zate/cc-plugins --skill run-swarm
Clone the repo
git clone --depth 1 https://github.com/Zate/cc-plugins

Made for: Claude Code, Codex.

Or install devloop, the plugin that ships this one along with the rest of its 19 skills, 6 agents.

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 run-swarm

README.md
[![agentmods](https://agentmods.dev/badge/skills/zate/cc-plugins/run-swarm.svg)](https://agentmods.dev/skills/zate/cc-plugins/run-swarm)
Your own site
<a href="https://agentmods.dev/skills/zate/cc-plugins/run-swarm"><img src="https://agentmods.dev/badge/skills/zate/cc-plugins/run-swarm.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,797 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 $0.00017 $0.01797
Opus 5 $0.00009 $0.00898
Sonnet 5 $0.00003 $0.00359
Haiku 4.5 $0.00002 $0.00180

Measured 3d ago against content hash d0fcb1950370, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run-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.

plugins/devloop/skills/run-swarm/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Devloop Run Swarm

Execute plan tasks via fresh-context subagents. You are the orchestrator.

Bash hygiene: prefer quiet flags to minimize output (npm install --silent, git status -sb, pipe long output through | tail -n 20).

Monitor for validation commands: When the orchestrator runs test or build commands to validate phase completion, use Monitor for real-time streaming. Worker agents (swarm-worker, haiku-worker) also have Monitor available and should use it for long-running commands within their tasks.

Long-running commands that warrant Monitor: test suites (npm test, pytest, go test ./..., cargo test, make test), builds (npm run build, make, cargo build, tsc), and full-codebase linting (eslint ., ruff check ., golangci-lint run).

Orchestrator validation example:

Monitor({ description: "swarm validation tests", command: "npm test 2>&1 | grep --line-buffered -E 'PASS|FAIL|Error|passed|failed'", timeout_ms: 300000, persistent: false })

Fallback: if Monitor errors, use Bash directly.

Step 1: Check Plan State

Run ${CLAUDE_PLUGIN_ROOT}/scripts/check-plan-complete.sh .devloop/plan.md.

  • No plan: Show entry points (/devloop:plan) and STOP.
  • Complete: AskUserQuestion: Ship it, Archive, or Review. STOP.
  • Pending: Continue to Step 2.

Step 2: Parse Arguments

  • --max-tasks N: Max tasks before pausing.
  • --dry-run: List pending tasks and STOP.
  • --worktrees: Run each worker with isolation: "worktree". Each worker gets an isolated git worktree; the orchestrator merges results back after each batch. Off by default.

Also read the local config to detect git.worktree_isolation:

Bash: ${CLAUDE_PLUGIN_ROOT}/scripts/parse-local-config.sh

If git.worktree_isolation is true in the config, treat it as if --worktrees was passed. The CLI flag always wins: --worktrees enables isolation regardless of config.

Step 3: Gather Shared Context

Extract max 100 lines from CLAUDE.md (code style, patterns) and plan's Overview/Considerations. Store as shared context.

Read the full file on GitHub · 160 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 · 160 lines · 17 tokens per session scan A d0fcb1950370

Subscribe to this mod's changes

run-swarm is a skill published in the GitHub repository Zate/cc-plugins (10 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 1,797 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens