A development harness for Claude Code and Codex CLI, with role-based agents that can route work and send it through a review gate. It also includes optional modules for several programming languages and frameworks.

Use it to assign implementation, architecture, database, or review tasks to specialized agents, including work involving PHP, Python, JavaScript, React, Swift, and other listed tools.

It organizes different kinds of coding and review work instead of treating every task the same way. The available roles and modules can be enabled for the technologies a project uses.

dhpk — Plugin for Claude Code by hmj1026

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/hmj1026/dhpk

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/hmj1026/dhpk/package/github.svg)](https://agentmods.dev/plugins/hmj1026/dhpk/package)

Your own site

<a href="https://agentmods.dev/plugins/hmj1026/dhpk/package"><img src="https://agentmods.dev/badge/plugins/hmj1026/dhpk/package/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/hmj1026/dhpk/package"><img src="https://agentmods.dev/badge/plugins/hmj1026/dhpk/package.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 39 skills, 1 command, 1 agent, 3 hooks cost 3,101 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 94% copy Near-identical to another mod in the catalogue.

Security

Grade A, and why

dhpk 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 today.

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.

Origin

This is a copy

94% identical to dhpk — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

generated/claude-marketplace/package/.claude-plugin/plugin.json · 538 lines

How it starts

The opening of the file, as written. The whole thing — 538 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "dhpk",
  "displayName": "DHPK Dev Harness",
  "version": "0.66.4",
  "description": "Reusable Claude Code harness with role-based agents, routed commands, advisory reviewer dispatch, opt-in PHP, Yii, PHPUnit, Laravel, JavaScript, Python, React, Next.js, and iOS/Swift modules, plus a parallel Codex CLI projection.",
  "author": {
    "name": "hmj1026",
    "url": "https://github.com/hmj1026"
  },
  "license": "MIT",
  "homepage": "https://github.com/hmj1026/dhpk",
  "keywords": [
    "harness",
    "codex",
    "code-review",
    "php",
    "yii",
    "phpunit",
    "laravel",
    "vue",
    "swift",
    "ios",
    "swiftui"
  ],
  "skills": [
    "./skills/"
  ],
  "agents": [
    "./agents/agy-worker.md",
    "./agents/architect.md",
    "./agents/code-reviewer.md",
    "./agents/codex-reasoner.md",
    "./agents/codex-reviewer.md",
    "./agents/codex-worker.md",
    "./agents/database-reviewer.md",
    "./agents/deep-reasoner.md",
    "./agents/doc-reviewer.md",
    "./agents/doc-updater.md",
    "./agents/docs-lookup.md",
    "./agents/e2e-runner.md",
    "./agents/fast-worker.md",
    "./agents/frontend-reviewer.md",
    "./agents/harness-reviser.md",
    "./agents/migration-reviewer.md",
    "./agents/performance-analyzer.md",
    "./agents/planner.md",
    "./agents/python-build-resolver.md",
    "./agents/refactor-cleaner.md",
    "./agents/rust-build-resolver.md",
    "./agents/security-reviewer.md",
    "./agents/silent-failure-hunter.md",
    "./agents/smoke-tester.md",
    "./agents/swift-build-resolver.md",
    "./agents/tdd-guide.md",
    "./agents/type-design-analyzer.md",
    "./agents/ui-ux-verifier.md",
    "./agents/version-matrix-impact-reviewer.md",
    "./modules/library-author/agents/polyfill-reviewer.md"
  ],
  "commands": [
    "./commands/",
    "./modules/js/commands/"
  ],
  "userConfig": {
    "hook_profile": {
      "type": "string",
      "title"

Read the full file on GitHub · 538 lines

Contents

What it installs

The manifest is a name and a version. 39 skills, 1 command, 1 agent, 3 hooks travel with it, and installing the plugin installs all of them — 3,101 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.

today Changed 68d1b8db84a2
yesterday Changed · -16 lines ea5c3050a904
2d ago Changed 7f451ccb6fde
8d ago Changed ce5d458c8760
10d ago Changed · -2 lines f26b40694a5c
15d ago Changed 3cbc1d05276c
18d ago Changed 258b075a0c28
20d ago Changed 00b74ebfc9a6
21d ago Changed a7b9f8cb7530
22d ago First seen · 556 lines scan A efa2a7a0df7a

Subscribe to this mod's changes

dhpk is a plugin published in the GitHub repository hmj1026/dhpk (2 stars, last pushed today), licensed MIT. 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. It is 94% identical to dhpk, differing in 0 lines, and is treated as a copy.

Building agents Claude Code Code review OpenSpec ai-tooling claude-code-plugin harness

mumei

Quality Enforcement Layer for Claude Code — Hook-gated SDD (spec & plan vehicles), Wave commits, and grounded multi-agent code review.

iroha924/mumei · not measured

argus-claude marketplace

Multi-agent code quality and architecture review with cross-validation.

josstei/argus-claude · not measured

argus

Multi-agent code quality and architecture review with cross-validation.

josstei/argus-claude · not measured

mad-scientist-skills

Architecture auditing (beta: Hexagonal/Ports & Adapters, Domain-Driven Design, Clean Architecture, SOLID principles, coupling/cohesion analysis, bounded context assessment), C4 architecture diagrams (Structurizr DSL), cognitive interface auditing (GOMS task models, Norman's Gulfs, Wood 7-layer error tolerance, Gergle…

karsten-s-nielsen/mad-scientist-skills · not measured

piercelamb-plugins marketplace

Claude Code plugins by Pierce Lamb.

piercelamb/deep-implement · not measured

humanizer

Rewrite AI-sounding text so it reads like the writer without changing what it says.

blader/humanizer · not measured