A workflow for running several approved development phases in parallel, each in its own workspace. It can show their status, launch them unattended, or stop individual members.

Use it to launch one to four approved phases, monitor a development fleet, or tear down a completed member.

It keeps parallel work isolated and makes progress across multiple phases visible. It also provides controlled cleanup and merging options after the work is validated.

power-fleet — Skill for Claude Code and Codex by pwdev-solucoes

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.

Any agent

npx skills add pwdev-solucoes/pwdev-claude-marketplace --skill power-fleet

Clone the repo

git clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplace

Made for: Claude Code, Codex.

Or install pwdev-power, the plugin that ships this one along with the rest of its 15 skills, 3 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/power-fleet/github.svg)](https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/power-fleet)

Your own site

<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/power-fleet"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/power-fleet/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/power-fleet"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/power-fleet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,787 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.

Model	Per session	Once invoked
Fable 5.1	$0.00038	$0.01787
Opus 5	$0.00019	$0.00894
Sonnet 5	$0.00008	$0.00357
Haiku 4.5	$0.00004	$0.00179

Measured 8d ago against content hash 583a4005bd7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

power-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-power/skills/power-fleet/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Operate a Fleet

Read fleet, cmux, safety, and artifacts before acting.

Routes

Route	Meaning
`<slug...>`	launch 1–4 approved phases as a visual panel — the default
`<slug...> --auto`	launch them unattended, one workspace each, as the fleet did before panels
`<slug...> --via-kanban`	launch through the Hermes Kanban board — see kanban
`--status`	one-shot dashboard
`--teardown <slug> [--merge]`	stop one member
`--teardown --all`	stop every validated member, one call each

Pass --merge only when the human explicitly asks for it.

Launch

Visual is the default. A panel is one cmux workspace holding one pane per member, each pane an interactive provider session in its own worktree, seeded with that phase's brief. The human watches all of them at once and steers any of them. --auto selects the previous behaviour: unattended members, one workspace each, structured results and correction cycles.

Tell the human, before launching a panel, that every pane opens on a folder-trust prompt and waits there: each worktree is a path the provider has never seen, and the permission flag gates tools, not folders. One answer per pane, given by them. A panel that looks stuck on arrival is usually this.

A panel holds 1 to 4 members. Four panes is where a grid stops being readable, and an unreadable panel defeats the point of having one. Only one panel may be active at a time: a second one cannot reuse the first's workspace without splitting into it and typing a privileged command into a live shell, which is exactly what the packaged scripts exist to avoid.

Inspect repository status and confirm a named current branch. Read config.json and the requested spec.md and plan.md. Never read a generated fleet environment file.
Resolve scripts from this installed skill at ../../scripts/. Call only the packaged fleet scripts; never assemble a provider command yourself.
Use the launcher of the runtime you are, and never another. The runtime is fixed by that choice, recorded in the member, and refused by a runner bound to a different one. There is no default and no override.

Read the full file on GitHub · 123 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

agents/openai.yaml 187 B

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.

8d ago First seen · 123 lines · 38 tokens per session scan A 583a4005bd7c

Subscribe to this mod's changes

power-fleet is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 38 tokens to every session and 1,787 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 2026-09-03.

Git and workflow Project management

mcore-split-pr

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

NVIDIA/skills · 25 tokens

shiplog

Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.

aeonfun/aeon · 46 tokens

llxprt-issue-workflow

Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the stepfun-37 smoke test), open code review (ocr), PR…

vybestack/llxprt-code · 87 tokens

power-fleet