analysis
Create structured analyses with numbered findings, execution plans, and task materialization
spec
Author a rulebook task spec interactively — research, draft, ask the user clarifying questions, confirm, then create the tasks in rulebook ready for /rulebook-driver. Use when the user wants to plan/spec a feature before implementing.
Claude Code
Tool: Anthropic Claude Code CLI (`npm install -g @anthropic-ai/claude-code`)
Claude
Tool: Anthropic Claude API with 200K context window
Karpathy Guidelines
Behavioral guidelines to reduce common LLM coding mistakes — overcomplication, sloppy refactors, hidden assumptions, weak goals. Use when writing, reviewing, or refactoring code. Auto-applies; invoke explicitly via /karpathy-guidelines or 'follow karpathy discipline'.
Rulebook Task Management
Spec-driven task management for features and breaking changes with OpenSpec-compatible format
accessibility
Accessibility audit for WCAG compliance and usability
api-design
Design or review API endpoints (REST/GraphQL)
architect
Architecture review, design decisions, and ADR writing
build-fix
Diagnose and fix build failures or CI issues
db-design
Database schema design, migrations, and query optimization
debug
Systematic debugging workflow for bugs and test failures
deploy
Prepare deployment artifacts and verify CI/CD readiness
docs
Generate or update project documentation based on recent changes
migrate
Plan and execute migrations (database, API, framework)
perf
Performance analysis, profiling, and optimization
refactor
Identify code smells and execute safe refactorings
research
Explore codebase and gather context about a topic or area
review
Deep code review of recent changes or specified files
security-audit
Run a security audit on the project (dependencies, secrets, OWASP)
Ada
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
C
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
C++
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
C#
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Dart
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Elixir
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Erlang
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Go
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Haskell
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Java
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
JavaScript
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Julia
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Kotlin
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Lisp
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Lua
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Objective-C
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
PHP
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Python
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
R
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Ruby
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Rust
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
SAS
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Scala
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Solidity
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
SQL
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Swift
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
TypeScript
TypeScript language rules with strict mode, testing, linting, and CI/CD best practices
Zig
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).