By pau-vega
Streamline git workflow with /commit, /commit-push-pr, and /clean-gone commands
Clean up local branches that have been deleted from the remote repository
Complete workflow — commit, push, and create a pull request in one step
Create a git commit with an automatically generated message based on staged and unstaged changes
Cleans up local branches that have been deleted from the remote repository (marked as [gone]). Removes associated worktrees before deleting branches. <example> Context: User wants to clean up stale local branches user: "/clean-gone" assistant: "I'll use the clean-gone-agent to remove stale branches." <commentary>User running /clean-gone triggers this agent.</commentary> </example> <example> Context: User's branch list is cluttered after merging many PRs user: "Clean up my local branches" assistant: "I'll dispatch the clean-gone-agent to prune branches deleted from remote." <commentary>Any request to clean stale branches triggers this agent.</commentary> </example>
Creates a git commit with an automatically generated commit message based on staged and unstaged changes. Reviews diff, examines recent commit history to match repo style, stages files, and creates the commit. <example> Context: User wants to commit their changes user: "/commit" assistant: "I'll use the commit-agent to stage and commit your changes." <commentary>User running /commit triggers this agent.</commentary> </example> <example> Context: User finished a coding session and wants to save progress user: "Commit everything I just did" assistant: "I'll dispatch the commit-agent to review and commit your changes." <commentary>Any request to commit changes triggers this agent.</commentary> </example>
Complete workflow agent that commits changes, pushes to a remote branch, and creates a pull request. Handles branch creation, commit message generation, and PR description with summary and test plan. <example> Context: User wants to commit, push, and open a PR user: "/commit-push-pr" assistant: "I'll use the commit-push-pr-agent to handle the full workflow." <commentary>User running /commit-push-pr triggers this agent.</commentary> </example> <example> Context: User finished a feature and wants to submit it user: "Push this and open a PR" assistant: "I'll dispatch the commit-push-pr-agent to commit, push, and create the PR." <commentary>Any request to push and open a PR triggers this agent.</commentary> </example>
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 curated collection of reusable skills, agents, and hooks — typescript-rules
and jsdoc-standards — installable into Claude Code, Cursor, or OpenCode
with a single command. Source files are runtime-neutral; the installer
translates per-target so no runtime is privileged.
npx devkit-ai
Ctrl-C at any prompt is a clean exit — no files are written until you confirm at the end of the prompt flow.
| Editor | project / project-local | user-global |
|---|---|---|
| Claude Code | <cwd>/.claude/ | ~/.claude/ |
| Cursor | <cwd>/.cursor/ | ~/.cursor/ |
| OpenCode | <cwd>/.opencode/ | ~/.config/opencode/ |
Inside each target the installer writes the standard subdirectories — skills/,
commands/, agents/, and either hooks/hooks.json (Claude Code, OpenCode) or
hooks.json at the root (Cursor). For project-local scope, the installer maintains a
delimited block in <cwd>/.gitignore listing every file it wrote, so re-running the
installer replaces the block in place and never duplicates entries:
# >>> Devkit-AI
.claude/skills/typescript-conventions/SKILL.md
.claude/commands/ts-review.md
...
# <<< Devkit-AI
hooks.json; it expects a
TypeScript plugin instead. Skills and commands are installed; real-time enforcement
hooks won't fire under OpenCode until a TypeScript port ships.agents/*.md from typescript-rules and jsdoc-standards is not copied
for Cursor targets. The skills and commands carry the relevant context.~/.cursor/hooks.json and
~/.cursor/hooks/ are formally documented. Commands, rules, and skills at user scope
follow the same shape but are not officially documented by Cursor.model: sonnet, ${CLAUDE_PLUGIN_ROOT}).
For OpenCode targets, the installer drops the model line (so the agent inherits
the user's opencode.json model — any provider), adds mode: subagent, removes
Claude Code's allowed-tools: [Agent], and rewrites plugin-root paths to ...
The body of every agent and command reads the same in both runtimes.| Flag | Effect |
|---|---|
--dry-run | Print every file that would be written, without touching disk. Existing destinations are listed as would write (overwrites existing) — no prompts fire. |
--help | Show usage and exit. |
--version | Print the installer version and exit. |
Releases are managed by release-please. On every push to main, release-please opens (or
updates) a PR that bumps the version in package.json and .claude-plugin/marketplace.json
and appends a changelog entry. Merging that PR creates a GitHub release with a vX.Y.Z tag,
which triggers the publish job in .github/workflows/release-please.yml. That job runs
npm pack --dry-run (sanity check) and then npm publish to the public npm registry,
authenticated by an NPM_TOKEN secret (an npm access token with publish permissions,
stored in the repository's GitHub secrets).
A plugin that enforces TypeScript coding conventions with automatic validation, code review, and a dedicated reviewer agent.
npx claudepluginhub pau-vega/devkit-ai --plugin commit-commandsA collection of developer workflow skills for planning, design review, and product requirements.
JSDoc documentation standards with three enforcement levels (Minimal, Standard, Strict), automatic warnings, and on-demand review
TypeScript coding conventions with automatic validation, review command, and reviewer agent
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.