cheapsteak-agent-plugins

Manage a PR stacked on another unmerged branch, and re-point it onto main after the base merges. Use when the user says "stack this PR", "restack", "re-point the PR base", "rebase onto main after the base merged", or has a PR whose base branch just merged.

Run `/code-review` in a fresh-context subagent, triage and address findings, then re-review — looping until no significant findings remain. Use when the user says "subagent review loop", "review loop", "loop until clean", or asks to harden a branch/PR with iterative independent review. Argument is passed through to `/code-review` (default `high`).

Drive native Windows desktop GUI apps with cua-driver (cua-computer-use MCP) — read the screen, click, type, navigate menus/forms. Use when automating a Windows application's UI, ESPECIALLY when pixel clicks land in the wrong place on a high-DPI / scaled display, or when a legacy (Delphi/VCL/Win32) app's clicks "do nothing." Covers the DPI click-offset fix and headless foreground control.

Run a self-perpetuating, multi-agent improvement loop on ANY codebase (chat, ingest, a UI, infra — anything with tests). A committed backlog of file-disjoint, waved tasks is implemented in parallel by a background Workflow, verified, adversarially reviewed, fixed, committed, and then re-scouted into the next round's backlog. Use when the user wants to iteratively harden/improve a project across many tasks ("improve X", "run a round", "keep iterating on Y", "set up an improvement loop"), to continue an existing loop ("run the next round"), or to fold a fresh ask into the next round. Requires the Workflow tool (multi-agent orchestration).

Monitor a PR for CI failures and reviewer comments, fix issues, and respond thoughtfully.

Browse any web app in a real browser using Playwright CLI. Use when asked to "check the app", "open the site", "look at the UI", "verify this page", "browse", or diagnose frontend behavior. General-purpose — not tied to any specific app.

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".

Create a background polling loop that monitors an external system and wakes Claude only when something changes. Use when the user says "monitor", "watch", "keep an eye on", "poll", "wait for", or wants to be notified when something external finishes or changes (CI, deployments, build jobs, API status, review approvals, etc.).

Stress-test any artifact by spawning an Adversary agent (finds problems) then a Counterweight agent (calibrates findings). Use when the user says "adversarial review", "challenge this", "stress test this", "red team this", or wants a second opinion on a design or implementation.

Schedule a delayed prompt that fires in the current Claude Code session at a target time, by launching a background bash task that exits at the target. Use when the user says "later", "in N hours/days", "wake me", "remind me in", "tomorrow", "next week", "schedule a follow-up", or wants to defer work past the 1-hour /loop ceiling. The wake payload can be a reminder, an instruction to execute, or a slash command.

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.

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.

Apollo Client cache updates for mutations. Use when implementing mutations that should update the UI without refetching queries.

Diagnose macOS memory usage and identify what's consuming RAM. Use when the system is slow, swap is high, or Activity Monitor shows suspicious numbers.

Guide for writing Claude Code hooks. Use when creating or modifying PostToolUse/PreToolUse hooks, making hooks emit warnings to Claude, or debugging why hook output isn't visible.

Create a new Claude Code plugin for any marketplace (local directory, GitHub, or custom). Handles plugin.json, SKILL.md, marketplace registration, and settings enablement. Use when the user says "create a plugin", "add a plugin", "new plugin", "make this a plugin", or wants to package a skill for distribution.

Anthropic's official guide to building Claude skills. Use when creating a new skill, editing an existing skill, reviewing skill structure, or debugging why a skill won't trigger.