Stats
Actions
Available In
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
By shouenlee
Fully agentic software engineering pipeline — from ticket intake through spec design, TDD implementation, code review, and PR creation. Orchestrates multiple agents and skills across five stages.
Reviews specs and plans for missing requirements, edge cases, and untested scenarios
Reviews specs and plans for performance bottlenecks, resource usage, and scalability
Converts a technical spec into a step-by-step implementation plan with file-level changes
Reviews specs and plans for long-term maintainability, readability, and code health
Reviews specs and plans for security vulnerabilities, unsafe patterns, and OWASP risks
Implement a ticket using TDD and review in a converging loop. Use when you have an approved spec and implementation plan. Spawns TddEngineer for implementation, delegates to deep-review for adversarial analysis, and auto-fixes findings in an autonomous loop (max 5 rounds) before gating user approval.
Create a pull request from a reviewed implementation branch. Use when the implementation and review stage is approved and you are ready to open a PR. Generates a conventional-commit title, structured body with ticket link, spec summary, test results, and review findings, then creates the PR via gh CLI.
Run a four-agent review on a technical spec or implementation plan. Use when a spec or plan needs evaluation from maintainability, security, efficiency, and completeness perspectives. Spawns four reviewer agents that write structured comment files, then merges all comments into the document in a single conflict-free pass.
Generate a technical spec and implementation plan for a ticket. Use when you have parsed requirements and need a detailed design before implementation. Orchestrates codebase exploration, spec authoring, autonomous review-fix loops, implementation planning, and plan review-fix loops across multiple agents.
Run the full software engineering pipeline from ticket to PR. Use when starting a feature, fixing a bug from a ticket, or driving end-to-end development from a Jira, Linear, or GitHub issue. Accepts a ticket ID or URL as argument and orchestrates intake, spec design, TDD implementation, code review, and PR creation with approval gates at each stage.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A cross-platform plugin marketplace for Claude Code and GitHub Copilot CLI.
Both tools share compatible plugin systems, so every plugin in this marketplace works with either tool out of the box.
| Plugin | Category | Components | Description |
|---|---|---|---|
| code-review | code-quality | skill, agent | Analyzes code for bugs, security issues, performance problems, and readability |
| make-skill-template | development | skill | Scaffolds new Agent Skills with proper frontmatter and directory structure |
| commit-changes | git | skill, hook | Reviews diffs and creates well-structured commits, splitting by logical concern |
| gh-pr-tools | git | 4 skills, hook | GitHub PR tools — review PRs, resolve comments, check thread status, create PRs |
| python-lint-fix | code-quality | skill, hook, reference | Runs ruff + mypy + bandit on Python files, explains violations, auto-fixes |
| ci-pipeline | workflow | skill, agent, hook | Generates GitHub Actions workflows and diagnoses CI failures |
| release-notes | git | skill, hook | Generates changelogs, bumps semver, publishes GitHub releases |
| docker-compose | development | skill, hook | Generates Dockerfiles and compose configs, adds services, checks anti-patterns |
| design-doc | docs | skill, agent, hook | Generates RFCs and ADRs with consistent numbering and format |
| task-breakdown | workflow | skill, hook | Decomposes features/issues into ordered subtasks with acceptance criteria |
| dep-manager | development | skill, hook | Manages Python deps — add, remove, audit vulnerabilities, detect unused |
| api-docs | docs | skill, hook | Generates API docs from FastAPI/DRF code and detects documentation drift |
| deep-wiki | docs | 8 skills, 3 agents | AI-powered wiki generator — Mermaid diagrams, onboarding guides, VitePress sites |
| deep-review | code-quality | skill, 3 agents | Adversarial code review with parallel Advocate, Skeptic, and Architect subagents |
| full-orchestration | workflow | docs | Fully agentic SWE pipeline — ticket intake, spec, TDD, review, and PR creation |
These are installable from the same marketplace via GitHub source references.
| Plugin | Source | Description |
|---|---|---|
| ralph-wiggum | harrymunro/ralph-wiggum | Autonomous coding loops — keeps Claude working until real completion criteria are met |
| context7 | upstash/context7 | Injects real-time, up-to-date library documentation into Claude's context |
| playwright-skill | lackeyjb/playwright-skill | Browser automation — writes and executes Playwright scripts for E2E testing |
| sentry-mcp | getsentry/sentry-mcp | Error monitoring — query Sentry issues, traces, and performance data |
| microsoft-playwright-mcp | microsoft/playwright-mcp | Official Microsoft Playwright MCP server for browser control and debugging |
# Add this marketplace
/plugin marketplace add shouenlee/ghcp-dev-plugin
# Install a plugin
/plugin install code-review@ghcp-dev-plugins
/plugin install python-lint-fix@ghcp-dev-plugins
/plugin install deep-review@ghcp-dev-plugins
# Add this marketplace
copilot plugin marketplace add shouenlee/ghcp-dev-plugin
# Install a plugin
copilot plugin install code-review@ghcp-dev-plugins
copilot plugin install python-lint-fix@ghcp-dev-plugins
copilot plugin install deep-review@ghcp-dev-plugins
Add to your project opencode.json or ~/.config/opencode/opencode.json:
{
"plugin": ["ghcp-dev-plugin@git+https://github.com/shouenlee/ghcp-dev-plugin.git"]
}
Restart OpenCode. All 31 skills and 16 agents install automatically. See .opencode/INSTALL.md for details.
/review # Review files changed in the working tree
/review src/ # Review all files in a directory
/lint # Run ruff + mypy + bandit on changed Python files
/deep_review # Adversarial multi-agent code review
/swe PROJ-123 # Full pipeline: ticket → spec → TDD → review → PR
/commit_changes # Smart commit splitting by logical concern
/pr-create # Create a PR from the current branch
/pr-review 123 # Full code review of a pull request
/pr-status 123 # Check review thread statuses
/resolve-pr 123 # Resolve open PR review threads
/release notes # Changelog from conventional commits since last tag
/release bump # Semver bump based on commit types
/release publish # Create GitHub release
npx claudepluginhub shouenlee/ghcp-dev-plugin --plugin full-orchestrationGenerates RFCs and Architecture Decision Records from feature descriptions, maintaining consistent numbering and format
Analyzes code for bugs, security issues, performance problems, and readability improvements
Decomposes feature descriptions and GitHub issues into ordered implementation subtasks with file-level scope and acceptance criteria
Manages Python dependencies — add, remove, audit for vulnerabilities, and detect unused packages
Intelligently reviews git diffs and creates well-structured commits, automatically splitting changes into multiple logical commits when needed
Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement
wshobsonOrchestration plugin. v1 use case: async development - turn ready issues into pull requests, then iterate on review feedback until a human takes over. Designed to host more orchestration use cases (refactoring, docs, audits) in future versions.
ai-driven-devAutonomous AI development pipeline that uses GitHub as a structured knowledge graph for Claude Code agents. Adds /work-on, /review-pr, /quality-gate, /orchestrate, and 20+ pipeline commands.
RapierCraftStudiosFull-stack orchestration with deployment, performance, security, and test automation
EricGrillSoftware engineering workflows with skills for planning, implementation, quality review, and structured thinking, plus a suite of specialist agents
chrisallenlaneMulti-agent orchestration framework for Claude Code, Gemini CLI, and Codex CLI — 19 agents, 14 skills, 16 commands, quality gates, TDD enforcement
dsifry