A spec-driven development plugin for Claude Code that coordinates specialised AI workers through planning, implementation, review, testing, verification, and roadmap work. It also provides project memory, optional parallel work, external coding tools, isolated workspaces, and an audit trail.

Use it to plan and implement requirements, delegate work to different coding agents, review changes, run quality checks, verify results, and manage larger multi-phase development tasks.

It structures software tasks around written requirements and repeated review instead of relying on one unchecked coding pass. Isolation and verification help separate experiments and catch problems before completion.

pwdev-code — Plugin for Claude Code 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.

Clone the repo

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

Made for: Claude Code.

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/plugins/pwdev-solucoes/pwdev-claude-marketplace/pwdev-code/github.svg)](https://agentmods.dev/plugins/pwdev-solucoes/pwdev-claude-marketplace/pwdev-code)

Your own site

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

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 2 skills, 22 commands, 8 agents, 6 hooks cost 982 tokens a session between them.

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.

Security

Grade A, and why

pwdev-code 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 1mo 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/.claude-plugin/plugin.json · 26 lines

What it actually says

{
  "name": "pwdev-code",
  "displayName": "PWDEV Code — Spec-Driven Development",
  "version": "2.4.0",
  "description": "Spec-driven development framework — hybrid orchestration with 8 real subagents (executor, advisor, simplifier, code-reviewer, QA, adversarial verifier, researcher, roadmap), per-task model routing by complexity, curated project memory graph feeding every spawn, opt-in parallel waves with worktree isolation, /pwdev-code:fleet for running multiple phases end-to-end (plan→execute→review→verify) unattended in isolated worktree+docker+tmux sessions, external CLI delegation (codex, opencode, kimi, gemini, kiro + smart /delegate), optional external reviewer CLI, strict dual-verifier mode, 6 phases with correction loops, deterministic SQLite audit via hooks, and extensible skills that turn requirements into verified, traceable code.",
  "author": {
    "name": "Paulo Soares",
    "url": "https://github.com/soarescbm"
  },
  "homepage": "https://github.com/pwdev-solucoes/pwdev-claude-marketplace",
  "repository": "https://github.com/pwdev-solucoes/pwdev-claude-marketplace",
  "license": "Apache-2.0",
  "keywords": [
    "claude-code",
    "claude-plugin",
    "workflow",
    "memory",
    "agents",
    "subagents",
    "hooks",
    "software-development",
    "spec-driven",
    "quality-assurance"
  ]
}

Contents

What it installs

The manifest is a name and a version. 2 skills, 22 commands, 8 agents, 6 hooks travel with it, and installing the plugin installs all of them — 982 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

1mo ago First seen · 26 lines scan A e02ce291a63a

Subscribe to this mod's changes

pwdev-code is a plugin published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (3 stars, last pushed 10d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Building agents

pwdev-code

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Nothing flagged

What it actually says

What it installs

What this file has done since we first saw it

Other plugins, from other repositories

humanizer

claude-plugins-official marketplace

nextjs

themes-example

knowledge-work-plugins marketplace

superpowers