Agent Claude Code
MUST BE USED PROACTIVELY after writing or modifying any code. Reviews against project standards, TypeScript strict mode, and coding conventions. Checks for anti-patterns, security issues, and performance problems.
Agent Claude Code
Git workflow agent for commits, branches, and PRs. Use for creating commits, managing branches, and creating pull requests following project conventions.
Command Claude Code
Execute API calls using OpenAPI specifications via Restish.
Command Claude Code
Determine what to work on next by analyzing project state, recent history, and open items.
Command Claude Code
Build or update a personal wiki from project context, local notes, and connected sources.
Hook Claude Code
Runs when a session starts, running entire hooks claude-code session-start. From stackmemoryai/stackmemory.
Hook Claude Code
Runs when a session ends, running entire hooks claude-code session-end (2 commands). From stackmemoryai/stackmemory.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, running entire hooks claude-code user-prompt-submit. From stackmemoryai/stackmemory.
Hook Claude Code
Runs when the agent finishes a response, executing gepa-session-hook.js via node (2 commands). From stackmemoryai/stackmemory.
Hook Claude Code
Runs before the agent uses a tool for Task tool calls, running entire hooks claude-code pre-task. From stackmemoryai/stackmemory.
Hook Claude Code
Runs after a tool call finishes for Task and TodoWrite tool calls, running entire hooks claude-code post-task (2 commands). From stackmemoryai/stackmemory.
Settings file Claude Code
Agent settings declaring 6 hook events (SessionStart, SessionEnd, UserPromptSubmit, Stop).
MCP server Claude CodeCodexCursor +2
MCP server "raindrop" as configured in stackmemoryai/stackmemory. Launched with /Users/jwu/.raindrop/bin/raindrop workshop mcp.
Instructions file
Claude Code instructions for stackmemoryai/stackmemory, covering croissant.ai — agent guide, stack, project structure, key files and detailed guides.
Command Claude Code
Postmortem analysis of cluster failures → OPTIMIZE PROMPTS to work for EVERY use case.
Command
Run stackmemory capture to commit current work and generate a handoff prompt for the next session.
Command
Run /summary internally, then audit what scripts, skills, commands, or memories need updating based on this session's work.
Command
Chain /stop done → /clear → /start in one command. Use when switching contexts or resetting after a long session.
Command
Run stackmemory restore to load context from the last handoff and resume where you left off.
Command
Load memory, restore last handoff, review recent history, and suggest what to work on.
Command
Run /summary → /capture → /learn, then either /compact or clear based on whether work remains.
Command
Generate a concise summary of work done in the current conversation.
Plugin Claude Code
Implementation of the Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.
Command
Cancel active Ralph Wiggum loop.