tmc/it2/claude-code-integration
Claude Code and agent skill by tmc/it2
- community
Checking that the SKILL.md file is still in the repository.
Use when working with Claude Code sessions in iTerm2 - detecting Claude sessions, checking their status, linking sessions, or coordinating multiple Claude instances.
Install
npx vskill@latest install tmc/it2/claude-code-integrationSKILL.md
Claude Code Integration
Guidance for interacting with Claude Code sessions running in iTerm2.
When to Use
- Detecting which iTerm2 sessions are running Claude Code
- Checking the status of Claude Code sessions (idle, working, waiting for input)
- Coordinating multiple Claude Code sessions
- Monitoring Claude Code session activity
- Setting up multi-agent Claude Code workflows
When NOT to Use
- For general terminal automation (use session-orchestration skill instead)
- When not working with Claude Code specifically
- For Claude API interactions (this is for the CLI tool in terminals)
Quick Start
Detecting Claude Code Sessions
By Process Name
By Session State
Claude Session Indicators
A session is likely running Claude Code if:
- Process name contains "claude" or "node" (Claude Code's runtime)
- Screen content shows Claude Code UI elements (╭─, tool use blocks, etc.)
- Session has specific environment variables set
Session Status Detection
Modal Detection
Claude Code shows modal dialogs for permissions, confirmations, etc.
Activity Detection
Session Linking
Link iTerm2 sessions to their Claude Code session files:
Multi-Claude Workflows
Setting Up Parallel Claude Sessions
Monitoring Multiple Sessions
Screen Content Analysis
Getting Claude's Output
Parsing Claude UI Elements
Claude Code's TUI has recognizable patterns:
╭─/╰─- Message box borders●- Working indicator?- Question/prompt indicator- Tool use blocks with specific formatting
Best Practices
- Always check for modals before sending input to Claude sessions
- Use badges with session ID prefix for visual tracking
- Monitor state before automated interactions
- Verify screen content matches expected state before proceeding
- Use quiet flags (
-q) when capturing session IDs for scripts - Include response hints when messaging other sessions - always tell them how to respond back (see workflows/multi-agent.md)
Advanced Usage
See references/state-detection.md for detailed state analysis. See references/ui-patterns.md for parsing Claude Code output. See workflows/multi-agent.md for coordinating multiple Claude instances.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/it2-skills/skills/claude-code-integration/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/tmc/it2/claude-code-integration)