fleet

fleet is a command for Claude Code from pwdev-solucoes/pwdev-claude-marketplace. It costs 35 tokens per session (1,831 once invoked), scanned A, original, Apache-2.0.

A command that runs several already-designed roadmap phases at the same time. Each phase works in its own Git worktree, Docker Compose environment, and tmux window; a worktree is a separate working copy of a Git repository.

In plain words
What is it for?
Running multiple prepared development phases concurrently and monitoring their isolated coding-agent pipelines.
Why use it?
It prevents parallel phases from interfering with one another and coordinates planning, implementation, review, and verification. The phases must already have approved specifications and decisions.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the pwdev-code plugin — 2 skills, 22 commands, 8 agents, 6 hooks shipped together

Good fit Running multiple prepared development phases concurrently and monitoring their isolated coding-agent pipelines.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add pwdev-solucoes/pwdev-claude-marketplace
Claude Code
/plugin install pwdev-code

Made for: Claude Code.

Or install pwdev-code, the plugin that ships this one along with the rest of its 2 skills, 22 commands, 8 agents, 6 hooks.

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 fleet

README.md
[![agentmods](https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/fleet.svg)](https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/fleet)
Your own site
<a href="https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/fleet"><img src="https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/fleet.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,831 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 $0.00035 $0.01831
Opus 5 $0.00017 $0.00915
Sonnet 5 $0.00007 $0.00366
Haiku 4.5 $0.00003 $0.00183

Measured 8d ago against content hash d0d4f13645d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

fleet 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 8d 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/pwdev-code/commands/fleet.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pwdev-code:fleet — Parallel Phase Fleet (worktree + tmux + docker)

Role (orchestrator — you dispatch the fleet, you never implement)

You spin up, monitor, and tear down a small fleet (max fleet.max_concurrent, default 3) of fully isolated, unattended pipelines — one per phase-slug. Each pipeline runs plan → execute → review → verify end-to-end in its own git worktree, its own docker-compose stack on its own ports, and its own real claude process inside a tmux window. You yourself only shell out to the fleet scripts and report status — the actual work happens in scripts and in the spawned claude processes, not in your context.

This command does not run discover or design — every target phase-slug must already have spec.md + decisions.md (i.e. /pwdev-code:design was already run and approved by a human). simplify is also excluded from the default pipeline (its APPLY step needs per-ID human approval, which is not available headless).

⚠️ Read before using

  • Each pipeline runs claude -p headless, with fleet.permission_mode (default bypassPermissions) — it accepts edits and runs Bash without asking. This is only acceptable because it runs inside an isolated git worktree (never your main working tree) and an isolated docker-compose stack (never your main environment). It never pushes, never merges to your current branch, and never removes a worktree on its own.
  • Any place the underlying commands (plan, execute, review, verify) would normally pause for human approval, the headless session is instructed to proceed automatically instead. That means plans and fixes in a fleet run are not human-reviewed until you look at the diff — review it before you merge.
  • Merging a fleet branch back into your current branch (--teardown --merge) is a separate, explicit step you run yourself.

Input

$ARGUMENTS:

  • <phase-slug> [phase-slug...] (1 to fleet.max_concurrent slugs) → start a fleet
  • --status → print the current fleet table once (no tmux needed)
  • --teardown <slug> [--merge] → stop and clean up one fleet member
  • --teardown --all [--merge] → teardown every active fleet member

Read the full file on GitHub · 157 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. 8d ago First seen · 157 lines · 35 tokens per session scan A d0d4f13645d6

Subscribe to this mod's changes

fleet is a command published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 1,831 once invoked, about $0.0002 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.