A development workflow bundle for GitHub-based projects. It covers issue breakdown, issue fixes, commits, releases, code-review fixes, post-merge cleanup, project setup, and Playwright browser tests.

Use it to bootstrap an empty project, diagnose an existing repository setup, break down and resolve GitHub issues, prepare releases, respond to code reviews, and create or debug Playwright end-to-end tests.

It keeps common steps in the development lifecycle in one place instead of requiring separate procedures for each task. It also records project state and checks whether an existing repository's agent setup is connected correctly.

dev — Plugin for Claude Code by YoungjaeDev/my-claude-plugins

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/YoungjaeDev/my-claude-plugins

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/youngjaedev/my-claude-plugins/dev/github.svg)](https://agentmods.dev/plugins/youngjaedev/my-claude-plugins/dev)

Your own site

<a href="https://agentmods.dev/plugins/youngjaedev/my-claude-plugins/dev"><img src="https://agentmods.dev/badge/plugins/youngjaedev/my-claude-plugins/dev/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/youngjaedev/my-claude-plugins/dev"><img src="https://agentmods.dev/badge/plugins/youngjaedev/my-claude-plugins/dev.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 12 skills, 3 agents cost 2,312 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

dev 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.

plugins/dev/.claude-plugin/plugin.json · 25 lines

What it actually says

{
  "name": "dev",
  "version": "5.3.3",
  "description": "Back half of the development flow, from a PR ready for review to merge and cleanup; the front half (idea -> spec -> tickets -> PR) belongs to Matt's skills (mattpocock-skills). GitHub workflow: commit-and-push, release, review-loop (unified CodeRabbit + ChatGPT-Codex review loop with autonomous apply/defer/skip judgment and rate-limit fallback), post-merge (cleanup only: leftover reviews, branch, issues, project status, About line; lessons go to /retro), session-handoff (chat-only end-of-session summary for a fresh agent), orchestrate (subagent orchestration: job cards, model x effort worker presets, disjoint file ownership, bounded re-query, orchestrator-owned verification), flow (router over Matt's front half and dev's back half plus product-repo setup, no side effects of its own). Project setup: new (first-day bootstrap: interview, .claude/ scaffold, CLAUDE.md + AGENTS.md with Codex reviewer guidelines, gh repo create) and wiring (14-axis harness diagnostic for an existing repo, read-only until approved). Playwright E2E harness: e2e-setup, e2e-author, e2e-debug wrap Playwright's planner/generator/healer agents (planner/generator explore via playwright-cli, healer via the playwright-test MCP server); never overwrite an existing playwright.config and degrade gracefully without Playwright.",
  "skills": [
    "./skills/commit-and-push",
    "./skills/release",
    "./skills/review-loop",
    "./skills/post-merge",
    "./skills/new",
    "./skills/wiring",
    "./skills/e2e-setup",
    "./skills/e2e-author",
    "./skills/e2e-debug",
    "./skills/session-handoff",
    "./skills/orchestrate",
    "./skills/flow"
  ],
  "agents": [
    "./agents/worker-standard.md",
    "./agents/worker-deep.md",
    "./agents/worker-max.md"
  ]
}

Contents

What it installs

The manifest is a name and a version. 12 skills, 3 agents travel with it, and installing the plugin installs all of them — 2,312 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 46faea231131
13d ago Changed 8fed7c0999c3
20d ago Changed b84451828426
23d ago Changed 27ea14ddaafe
25d ago Changed · -4 lines ea10f2eb857d
1mo ago Changed 9adc85e1dda5
1mo ago Changed · +1 lines bffa33df7da5
1mo ago Changed 14b105d0bc33
1mo ago Changed · +7 lines f93d0b2aca2b
1mo ago First seen · 21 lines scan A 5c3b09c96958

Subscribe to this mod's changes

dev is a plugin published in the GitHub repository YoungjaeDev/my-claude-plugins (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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

E2E testing Git and workflow Releases Testing

developer-essentials

Essential developer skills including Git workflows, SQL optimization, error handling, code review, E2E testing, authentication, debugging, and monorepo management.

HermeticOrmus/LibreUIUX-Claude-Code · not measured

ai-swift

Catches Xcode Cloud and TestFlight blockers before upload (XcodeGen pbxproj drift, static build numbers, missing ciscripts, macOS App Store entitlements/Info.plist, headless-CI keychain test failures, ad-hoc signing entitlement rejections, flaky-UITest release gating), diagnoses ITMS rejection emails and red CI logs.

charlesjones-dev/claude-code-plugins-dev · not measured

ship

End-to-end shipping workflow: smart staging with change cohesion analysis, conventional commits, test gates, push, and optional PR creation.

juanmhidalgo/claude-plugins · not measured

ai-stack

Useful AI things an engineer uses daily. Ships prodcheck (senior-engineer production review), prodtest (senior-QA test pass with Playwright), mergemain (context-aware merge of main into the current branch), shipit (clean commits and PRs, with or without AI attribution), and adonis-next-monorepo (scaffolds a verified…

nazmulnahid-git/Ai-Stack · not measured

hotfix

Test-first hotfix for a deployed bug — reproduce as a failing test, minimal fix, land it on both the mainline and the release branch.

optimiziramsi/skills · not measured

ok-prerelease-verification

PR readiness assessment for any GitHub repo, plus DWO prerelease verification checklist generator.

akurinnoy/ok_plugins · not measured