By cheapsteak
Branch, commit, push, PR, rebase, and review-feedback workflows on top of git + gh CLI
Fetch and analyze all feedback on the current PR to create a comprehensive implementation plan. Use when the user says "address pr feedback", "handle pr comments", "review pr feedback", "address review comments", or wants to systematically work through PR review threads.
Monitor a PR for CI failures and reviewer comments, fix issues, and respond thoughtfully.
Commit, push, and open a PR with a compelling title. Use when the user says "pr", "open a pr", "push and create pr", "commit and pr", wants to ship their branch, or before running "gh pr create".
Rebase the current branch onto a target branch with safe conflict resolution. Use when the user says "rebase", "rebase on main", "update my branch", "pull in latest changes from main", "sync with main", or when resolving rebase conflicts. Handles stashing uncommitted changes, generated file conflicts, and cascading conflict recovery.
Chang's Claude Code plugins — generic dev workflow, skill authoring, and macOS/web utilities.
# Add the marketplace
/plugin marketplace add https://github.com/cheapsteak/cheapsteak-agent-plugins.git
# Install individual plugins
/plugin install git-flow@cheapsteak-agent-plugins
/plugin install skill-authoring-kit@cheapsteak-agent-plugins
/plugin install agent-workflow@cheapsteak-agent-plugins
/plugin install macos-ops@cheapsteak-agent-plugins
/plugin install web-tools@cheapsteak-agent-plugins
/plugin install gql@cheapsteak-agent-plugins
Restart Claude Code after installation — plugins added mid-session don't load.
| Plugin | Version | Description |
|---|---|---|
git-flow | 0.2.0 | Commit, push, PR, rebase, review-feedback workflows on top of git + gh |
skill-authoring-kit | 0.1.0 | Build Claude skills, plugins, and hooks |
agent-workflow | 0.3.0 | Adversarial review, scheduled wake-ups, background-monitor polling, /explain command |
macos-ops | 0.1.0 | macOS sysadmin (memory diagnosis today) |
web-tools | 0.3.0 | Playwright-CLI-based browsing (cua-driver as alternative) |
gql | 0.1.0 | GraphQL / Apollo patterns |
| Plugin | Skills |
|---|---|
git-flow | pr, rebase, monitor-pr, address-pr-feedback |
skill-authoring-kit | skill-authoring, create-plugin, claude-hooks |
agent-workflow | adversarial-review, later, monitor |
macos-ops | diagnose-memory |
web-tools | browse |
gql | apollo-optimistic-updates |
cheapsteak-agent-plugins/
├── .claude-plugin/
│ └── marketplace.json
├── plugins/
│ └── <plugin-name>/
│ ├── .claude-plugin/
│ │ └── plugin.json
│ ├── skills/
│ │ └── <skill-name>/
│ │ └── SKILL.md
│ └── README.md
├── CHANGELOG.md
├── CLAUDE.md
└── README.md
When bumping a plugin's version, update all three:
plugins/<plugin>/.claude-plugin/plugin.json.claude-plugin/marketplace.jsonCHANGELOG.mdDeferred. Anthropic's plugin format works for Claude Code; for Codex we'd add an equivalent manifest per plugin once the format is settled.
MIT.
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.
npx claudepluginhub cheapsteak/cheapsteak-agent-plugins --plugin git-flowSlack-style channels for cross-session AI agent messaging
Build Claude skills, plugins, and hooks. Bundles skill-authoring guide, plugin scaffolder, and hook-output reference.
macOS sysadmin skills. Today: diagnose memory pressure and identify what's consuming RAM.
Session patterns for working with Claude: adversarial review (stress-test artifacts), later (schedule a delayed prompt), monitor (wake Claude when external state changes), and improvement-loop (self-perpetuating multi-agent improvement rounds).
Browse the web in a real browser to verify UI behavior, diagnose frontend issues, or take screenshots. Today: Playwright-CLI-based browsing, with cua-driver as an alternative for the user's already-open browser.
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).
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
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
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.