execute

execute is a command for Claude Code from pwdev-solucoes/pwdev-claude-marketplace. It costs 11 tokens per session (2,247 once invoked), scanned A, original, Apache-2.0.

A command that runs a prepared project plan by sending each task to a separate coding worker and tracking progress. It expects planning files created by earlier project steps.

In plain words
What is it for?
Use it to carry out tasks listed in project plan files, one at a time, while updating the project state. It is intended for projects using the pwdev-code planning workflow.
Why use it?
It keeps implementation work organized across independent tasks and preserves a short record of what has been completed. It also warns about uncommitted code and blocked reviews before continuing.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents; names the SlashCommand tool; mentions Claude Code.

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

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 execute

README.md
[![agentmods](https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/execute.svg)](https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/execute)
Your own site
<a href="https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/execute"><img src="https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/execute.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,247 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 5.1 $0.00011 $0.02247
Opus 5 $0.00005 $0.01123
Sonnet 5 $0.00002 $0.00449
Haiku 4.5 $0.00001 $0.00225

Measured 6d ago against content hash 63fb521e03a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 6d 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/execute.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pwdev-code:execute — Execute Phase

Role (orchestrator — you do NOT implement; the executor subagent does)

You coordinate the execution loop: pick the next task, spawn a fresh pwdev-code:executor subagent for it with a self-contained prompt, collect its short status, update state.md, and move on. Each task runs in a fresh context — this is the Fresh Context Model, for real.

Entry Gate

[ -d ".planning/phases/" ] || { echo "❌ No phases folder. Run /pwdev-code:design first."; exit 1; }
ls .planning/phases/*/plans/*.md >/dev/null 2>&1 || { echo "❌ No plans found. Run /pwdev-code:plan first."; exit 1; }

If .planning/state.md contains review_gate: BLOCKED and you are NOT running --fix → warn that review found critical findings and they should be addressed first.

Flow

STEP 0 — Language

Follow ${CLAUDE_PLUGIN_ROOT}/references/language.md (resolve lang from .planning/config.json; ask only if unset).

STEP 0.5 — Uncommitted Work Check

git status --short 2>/dev/null

If uncommitted code is detected → warn the human before spawning anything:

  • PT-BR: ⚠️ Codigo nao commitado detectado. Deseja commitar antes de continuar? (s/n)
  • EN: ⚠️ Uncommitted code detected. Commit before continuing? (y/n)

(Older versions generated an executor-context.md for stale sessions — no longer needed: every spawn is fresh and self-contained by design.)

STEP 1 — Build the Work Queue

cat .planning/state.md
ls .planning/phases/*/plans/*.md
  • Normal mode: pending plans, grouped by their Wave: header, respecting Depends on:. Honor --plan=PP / --wave=N filters.
  • --fix mode: the queue is .planning/phases/{slug}/verify/fix-*.md. Read fix_iteration from state.md (default 0). If fix_iteration >= 2 → STOP: present both verify reports' diff to the human and escalate — do not loop forever. Otherwise increment it in state.md.

STEP 2 — Execution Loop (per task, wave by wave)

For each task of the current wave, in order:

Read the full file on GitHub · 179 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. 6d ago First seen · 179 lines · 11 tokens per session scan A 63fb521e03a8

Subscribe to this mod's changes

execute is a command published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 17d ago), licensed Apache-2.0. It adds 11 tokens to every session and 2,247 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.