What is power-execute?

A workflow for executing an approved engineering plan one task at a time, with a separate implementer and review between tasks. A worktree is an isolated copy of a Git repository used to keep changes separate.

Use it to carry out a multi-task plan, track progress in a ledger, isolate work, and review each task as it is completed.

It prevents completed tasks from being repeated and keeps parallel or staged work organized. The pre-flight checks expose conflicts between tasks before implementation starts.

power-execute — 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-execute

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-execute/github.svg)](https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/power-execute)

Your own site

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

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,603 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	$0.00029	$0.01603
Opus 5	$0.00015	$0.00801
Sonnet 5	$0.00006	$0.00321
Haiku 4.5	$0.00003	$0.00160

Measured 3d ago against content hash dc50068d5824, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

power-execute 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/pwdev-power/skills/power-execute/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execute a Plan, Task by Task

Read collaboration, runtime, model-profiles, and safety before acting.

You are the controller. You dispatch, you adjudicate, you record. You do not implement and you do not fix. The moment you edit code yourself, every discipline below stops applying to that edit.

Setup

Ensure isolation with pwdev-power:power-worktree.
../../scripts/power-workspace.sh <slug> prints the working directory and creates ledger.md.
Read the ledger. Its first line names its plan. Tasks marked Task NN: complete are done — do not dispatch them again. A ledger belonging to a different plan is not yours; ignore it.

This check exists because the most expensive observed failure is a controller that lost its place and re-dispatched a whole sequence of finished tasks.
Pre-flight scan, before Task 01. Produce a table with one row per pair of tasks that share a file or an interface — what one produces against what the other consumes — and one row per task confirming its own text agrees with itself. Record every ruling you make in the ledger. "The scan is clean" without those rows is not a scan you ran.

Model selection

Codex inherits host or session model and reasoning-effort settings by default. Override only for an explicit user instruction, repository governance rule, configuration, or approved profile, after confirming a supported model-and-effort combination on that host.
Claude Code keeps explicit model routing on every dispatch. Apply the configured profile and the task's declared Complexity per model-profiles, using a model the runtime supports.
Hermes Agent follows hermes-tools and the runtime mapping. Use its documented Kanban route or run inline when per-dispatch selection is unavailable; never invent model, provider, or effort parameters.

Read the full file on GitHub · 151 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 190 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.

3d ago Changed · +10 lines dc50068d5824
6d ago First seen · 141 lines · 29 tokens per session scan A 32e4240ab1c3

Subscribe to this mod's changes

power-execute is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,603 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.

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-execute