From claudekit
Switches Claude's behavioral modes for the session to adjust communication style, output format, and problem-solving approach. Use for keywords like 'mode', 'brainstorm', 'token-efficient'.
npx claudepluginhub duthaho/claudekit --plugin claudekitThis skill uses the workspace's default tool permissions.
- User wants to change response style for the session
Activates task-specific AI modes (brainstorm, implement, debug, review, teach, ship, orchestrate) to optimize behavior for planning, coding, troubleshooting, reviewing, and shipping.
Injects behavioral rules for structured agent modes: tdd (red-green-refactor), debugging (4-phase root cause), sprint (pre-agreed criteria), verification (evidence-before-claims), brainstorm (design first), think (pause-reflect), orchestrate (task decomposition). Set LACP_CONTEXT_MODE to activate.
Mandates invoking relevant skills via tools before any response in coding sessions. Covers access, priorities, and adaptations for Claude Code, Copilot CLI, Gemini CLI.
Share bugs, ideas, or general feedback.
| Mode | Description | Best For |
|---|---|---|
default | Balanced responses, mix of explanation and code | General tasks |
brainstorm | More questions, multiple alternatives, explore trade-offs | Design, ideation |
token-efficient | Minimal explanations, code-only where possible | High-volume, cost savings |
deep-research | Thorough analysis, citations, confidence levels | Investigation, audits |
implementation | Jump straight to code, progress indicators | Executing plans |
review | Look for issues first, severity levels, actionable feedback | Code review, QA |
orchestration | Task breakdown, parallel execution, result aggregation | Complex parallel work |
Use natural language to switch modes for the session:
"switch to brainstorm mode" # Creative exploration
"use implementation mode" # Code-focused execution
"switch to token-efficient mode" # Compressed output
"back to default mode" # Reset
brainstorm → implementation → review → default
deep-research → implementation → default
token-efficient → [work on tasks] → default
Mode definitions: .claude/modes/
Customize modes by editing these files. Each mode adjusts:
writing-concisely — The token-efficient mode activates this skill's patternsbrainstorming — The brainstorm mode uses this skill's questioning approachexecuting-plans — Implementation mode pairs with plan executionsequential-thinking — Deep research mode leverages structured reasoning