Analyze Claude Code usage, cost, efficiency, and burn rate using ccusage and termgraph. Use when user says "usage", "cost", "spending", "tokens", "analyze usage", "how much did I spend", "usage report", "budget", "burn rate", "efficiency", "cache hits", "ccusage", "ccw", "ccp".

Turn ideas into designs through collaborative dialogue. Use when user wants to brainstorm, design features, explore approaches, or think through implementation before coding.

Inter-agent messaging via ccgram swarm. Use when communicating with other agents in the same tmux session — send messages, check inbox, discover peers, broadcast status, reply to requests, or spawn new agents. Activates on: peer messages, inbox, swarm, ccgram, broadcast, agent collaboration, ask another agent.

Smart git commits with logical grouping. Use when user says "commit", "commit changes", "save changes", "create commit", "bundle commits", "git commit", or wants to commit their work.

Validate and deploy infrastructure changes safely. Dry-run is the default. Never apply changes, especially destructive ones, without explicit confirmation. Keep going through each step — do not skip validation or the confirmation gate.

Validate and deploy Kubernetes, Terraform, Helm, Kustomize, GitHub Actions, and Docker configs. Use when user says "deploy", "deploy to staging", "apply changes", "terraform apply", "helm upgrade", "kubectl apply", "rollout", "deploy check", "validate deployment", "validate infrastructure", or wants to verify or apply infrastructure changes.

Stress-test ideas by spawning competing perspectives, then synthesize and ground-truth against code.

Update project documentation based on recent changes. Use when user says "update docs", "document", "add documentation", "update readme", "write docs", or wants to improve documentation.

Generate and run end-to-end tests using Playwright. Work through the steps sequentially. Keep going after failures — read the error, fix the script, and re-run until all tests pass.

Audit Claude Code configuration against latest features and best practices. Use when user says "evolve", "self-improve", "audit config", "what's new in claude code", "upgrade configuration", "check for improvements", "are we up to date".

Explore public GitHub repositories via DeepWiki AI-generated documentation. Use for understanding architecture, patterns, design decisions, and code organization of popular open-source projects. Use when user asks "how does X repo work", "explain architecture of Y", "what patterns does Z use", "explore repo", "deepwiki", or needs codebase-level understanding beyond API docs.

Identify every failing check, root-cause it, fix it, and verify the fix. Repeat until the build, tests, and linter are all clean. Do not declare done until every check passes.

Fix ALL issues via parallel agents with zero tolerance quality enforcement. Use when user says "fix", "fix issues", "fix errors", "fix all", "fix bugs", "fix lint", "fix tests", or wants to resolve code problems.

Review, refactor, and improve test quality. Use when user says "improve tests", "refactor tests", "test coverage", "combine tests", "table-driven", "parametrize", "test.each", "eliminate test waste", or wants to optimize test structure.

Review agent and skill instructions against rules derived from the Claude Opus 4.6 and Sonnet 4.6 system cards. Combines a fast regex pre-pass with deep model-based semantic review.

Extract learnings and generate project-specific customizations (CLAUDE.md, commands, skills, hooks). Use when user says "learn", "extract learnings", "what did we learn", "save learnings", "adapt config", or wants to improve Claude Code based on conversation patterns.

Library documentation via Context7. Use for API references, code examples, framework docs.

Infrastructure patterns for Kubernetes, Terraform, Helm, Kustomize, and GitHub Actions. Use when making K8s architectural decisions, choosing between Helm vs Kustomize, structuring Terraform modules, writing CI/CD workflows, or applying security best practices.

Query project history, past decisions, and known gotchas from claude-mem observations. Use when user asks "last session", "did we already", "what did we decide", "project history", "timeline", or "what happened with".