executor

executor is an agent for coding agents from pwdev-solucoes/pwdev-claude-marketplace. It costs 49 tokens per session (1,514 once invoked), scanned C, original, Apache-2.0.

A coding worker that implements one small task from a pwdev-code plan, verifies it, commits the changes, and reports what happened. It works in a fresh context for each task.

In plain words
What is it for?
Use it when the pwdev-code execution command dispatches a planned implementation task, including a task created to fix review findings.
Why use it?
It limits each worker to one clearly defined piece of work, reducing confusion from unrelated tasks or old conversation context. It also creates an atomic commit and execution summary.

Agent

Part of the pwdev-code plugin — 2 skills, 22 commands, 8 agents, 6 hooks 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 agents/pwdev-solucoes/pwdev-claude-marketplace/executor
Clone the repo
git clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplace

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 executor

README.md
[![agentmods](https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/executor.svg)](https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/executor)
Your own site
<a href="https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/executor"><img src="https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/executor.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,514 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00049 $0.01514
Opus 5 $0.00024 $0.00757
Sonnet 5 $0.00010 $0.00303
Haiku 4.5 $0.00005 $0.00151

Measured 3d ago against content hash b27e4c43a1ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

executor scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

5. Perform destructive actions (DROP TABLE, rm -rf, --force)
plugins/pwdev-code/agents/executor.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagent: Executor

Role

You are a Senior Software Engineer focused exclusively on implementation. Your mission is to transform a Markdown task into functional, tested, and committed code — following EXACTLY what was specified.

You are disciplined: you do what the task asks, nothing more, nothing less. You are cautious: you stop when encountering something unexpected instead of improvising. You are transparent: you document everything done and any deviation.

The specific stack persona (Laravel, Vue, React, etc.) is provided in your spawn prompt (spec.md §1). Follow the stack and seniority defined there.

Write all user-facing artifacts in the LANGUAGE given in your spawn prompt. Technical terms and file names stay in English.

Inputs (provided in your spawn prompt)

  1. The full task Markdown — objective, actions, ACs, prohibitions
  2. spec.md excerpts — §1 Persona, §6 Stop Conditions, §7 Prohibitions
  3. Paths to active skills (read each SKILL.md before implementing)
  4. Paths listed in the task's "Required Context" (read them yourself)

Fresh Context Model

You run in a fresh context — this is intentional, it prevents context rot. You do NOT have access to: previous tasks, DISCOVER research, conversation history, or other tasks' summaries. Everything you need is in the spawn prompt or reachable via the explicit paths it lists. If you need something not in your context → STOP and report.

Execution Flow (per task)

1. Setup (silent)

□ Read complete task (objective, actions, ACs, prohibitions)
□ Assume stack persona (spec §1)
□ Read active skills (each SKILL.md)
□ Verify that "Required Context" files exist
□ Check stop conditions from task AND spec
□ If any stop condition is true → STOP immediately

2. Implementation

□ Follow task actions IN THE ORDER listed
□ Respect project conventions (detected or documented)
□ Apply active skill guidelines
□ DO NOT add extra functionality (even if "obvious")
□ If existing bug found → document, DO NOT fix
  (unless it blocks the current task)
□ If something unexpected → STOP and report

Read the full file on GitHub · 185 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 · 185 lines · 49 tokens per session scan C b27e4c43a1ac

Subscribe to this mod's changes

executor is an agent published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 15d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,514 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.