prime
121disler/claude-code-is-programmable
Command Claude Code
Command "prime" from disler/claude-code-is-programmable, covering context prime, run the following commands and parallel read the following files.
disler/claude-code-is-programmable
Command Claude Code
Command "prime" from disler/claude-code-is-programmable, covering context prime, run the following commands and parallel read the following files.
Command Claude Code
READ README.md, THEN run git ls-files and eza --git-ignore --tree to understand the context of the project don't read any other files.
Command Claude Code
READ README.md, THEN run git ls-files and eza --git-ignore --tree to understand the context of the project don't read any other files.
Command Claude Code
Command "jprompt_ultra_diff_review" from disler/aider-mcp-server, covering ultra diff review, task 1: create diff.txt, code review, diff and task 2: git diff and append.
Command Claude Code
Run a multi aideraicode call with a sub agent call to fulfill the following tasks back to back in the most sensible order. If the given task(s) can be broken down into smaller tasks, do that. If tasks are dependent on certain changes to be made first, make sure to run the dependent tasks first. $ARGUMENTS.
MCP server Claude CodeCodexCursor +2
MCP server "aider-mcp-server" as configured in disler/aider-mcp-server. Launched with uv --directory . run aider-mcp-server --editor-model gemini/gemini-2.5-pro-previ.
Command Claude Code
Install Fixing Opus 5 — verify just, claude, herdr, jq, and pi, then confirm the compare loop is ready.
Agent Claude Code
Complete the work detailed to you end to end while tracking progress and marking your task complete with a summary message when you're done.
Command Claude Code
Install, configure, and verify the steer agent sandbox on this macOS device.
Command Claude Code
Install and verify the engineer's primary device for sending jobs to the agent sandbox.
Command Claude Code
Execute a task using steer (GUI) and drive (terminal) to control the entire macOS device.
Command Claude Code
Load foundational context about the steer codebase — architecture, apps, skills, and key patterns.
Skill Claude CodeCodex
Terminal automation CLI for AI agents. Use drive to create tmux sessions, execute commands, send keystrokes, read output, poll for patterns, run commands in parallel across sessions, and manage processes. Always use --json for structured output.
Skill Claude CodeCodex
Skill "steer" from disler/mac-mini-agent, covering steer — macos gui automation, commands, how to work, 1. know your environment first and 2. focus the app, then verify.
Agent Claude Code
UI validation agent that executes user stories against web apps and reports pass/fail results with screenshots at every step. Use for QA, acceptance testing, user story validation, or UI verification. Supports parallel instances. Keywords - QA, validation, user story, UI testing, acceptance testing, bowser.
Agent Claude Code
Browser automation agent. Use when you need to browse websites, take screenshots, interact with web pages, or perform browser tasks. Cannot run in parallel — only one instance at a time. Keywords - browse, screenshot, browser, chrome, bowser, ui testing.
Agent Claude Code
Headless browser automation agent using Playwright CLI. Use when you need headless browsing, parallel browser sessions, UI testing, screenshots, or web scraping. Supports parallel instances. Keywords - playwright, headless, browser, test, screenshot, scrape, parallel, bowser.
Command Claude Code
Search Amazon, add item(s) to cart, proceed to checkout, stop.
Command Claude Code
Visit a blog, find the latest post, summarize it, and save the summary.
Command Claude Code
Run a saved browser automation workflow with configurable skill, mode, and vision settings.
Command Claude Code
Build the codebase based on the plan.
Command Claude Code
List all available tools as TypeScript function prototypes with parameter and purpose comments.
Command Claude Code
Prime context by exploring the codebase structure and README.
Command Claude Code
Parallel user story validation — discovers YAML stories, fans out bowser-qa-agents, aggregates results.