{
  "schemaVersion": "1.0",
  "item": {
    "slug": "openclaw-claude-code",
    "name": "Claude Code Agent",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/Enderfga/openclaw-claude-code",
    "canonicalUrl": "https://clawhub.ai/Enderfga/openclaw-claude-code",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/openclaw-claude-code",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-claude-code",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "examples/basic-mcp.ts",
      "examples/chat-store.ts",
      "mcp_config.example.json",
      "package.json"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/openclaw-claude-code"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/openclaw-claude-code",
    "agentPageUrl": "https://openagent3.xyz/skills/openclaw-claude-code/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-claude-code/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-claude-code/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Claude Code Skill",
        "body": "Control Claude Code via MCP (Model Context Protocol). This skill unleashes the full power of Claude Code for openclaw agents, including persistent sessions, agent teams, and advanced tool control."
      },
      {
        "title": "⚡ Quick Start",
        "body": "# Start a persistent Claude session for your project\nclaude-code-skill session-start myproject -d ~/project \\\n  --permission-mode plan \\\n  --allowed-tools \"Bash,Read,Edit,Write,Glob,Grep\" \\\n  --max-budget 2.00\n\n# Send a complex task (Claude will autonomously use tools)\nclaude-code-skill session-send myproject \"Find all TODO comments and create GitHub issues\" --stream\n\n# Check progress\nclaude-code-skill session-status myproject"
      },
      {
        "title": "Use Persistent Sessions When:",
        "body": "✅ Multi-step tasks requiring multiple tool calls\n✅ Iterative development (write code → test → fix → repeat)\n✅ Long conversations needing full context\n✅ Agent needs to work autonomously\n✅ You want streaming real-time feedback"
      },
      {
        "title": "Use Direct MCP Tools When:",
        "body": "✅ Single command execution\n✅ Quick file read/write\n✅ One-off searches\n✅ No context needed between operations"
      },
      {
        "title": "Basic MCP Operations",
        "body": "# Connect to Claude Code MCP\nclaude-code-skill connect\nclaude-code-skill status\nclaude-code-skill tools\n\n# Direct tool calls (no persistent session)\nclaude-code-skill bash \"npm test\"\nclaude-code-skill read /path/to/file.ts\nclaude-code-skill glob \"**/*.ts\" -p ~/project\nclaude-code-skill grep \"TODO\" -p ~/project -c\nclaude-code-skill call Write -a '{\"file_path\":\"/tmp/test.txt\",\"content\":\"Hello\"}'\n\n# Disconnect\nclaude-code-skill disconnect"
      },
      {
        "title": "Persistent Sessions (Agent Loop)",
        "body": "Starting Sessions\n\n# Basic start\nclaude-code-skill session-start myproject -d ~/project\n\n# With custom API endpoint (for Gemini/GPT proxy)\nclaude-code-skill session-start gemini-task -d ~/project \\\n  --base-url http://127.0.0.1:8082 \\\n  --model gemini-2.0-flash\n\n# With permission mode (plan = preview changes before applying)\nclaude-code-skill session-start review -d ~/project --permission-mode plan\n\n# With tool whitelist (auto-approve these tools)\nclaude-code-skill session-start safe -d ~/project \\\n  --allowed-tools \"Bash(git:*),Read,Glob,Grep\"\n\n# With budget limit\nclaude-code-skill session-start limited -d ~/project --max-budget 1.50\n\n# Full configuration\nclaude-code-skill session-start advanced -d ~/project \\\n  --permission-mode acceptEdits \\\n  --allowed-tools \"Bash,Read,Edit,Write\" \\\n  --disallowed-tools \"Task\" \\\n  --max-budget 5.00 \\\n  --model claude-opus-4-5 \\\n  --append-system-prompt \"Always write tests\" \\\n  --add-dir \"/tmp,/var/log\"\n\nPermission Modes:\n\nModeDescriptionacceptEditsAuto-accept file edits (default)planPreview changes before applyingdefaultAsk for each operationbypassPermissionsSkip all prompts (dangerous!)delegateDelegate decisions to parentdontAskNever ask, reject by default\n\nSending Messages\n\n# Basic send (blocks until complete)\nclaude-code-skill session-send myproject \"Write unit tests for auth.ts\"\n\n# Streaming (see progress in real-time)\nclaude-code-skill session-send myproject \"Refactor this module\" --stream\n\n# With custom timeout\nclaude-code-skill session-send myproject \"Run all tests\" -t 300000\n\nManaging Sessions\n\n# List active sessions\nclaude-code-skill session-list\n\n# Get detailed status\nclaude-code-skill session-status myproject\n\n# View conversation history\nclaude-code-skill session-history myproject -n 50\n\n# Pause and resume\nclaude-code-skill session-pause myproject\nclaude-code-skill session-resume-paused myproject\n\n# Fork a session (create a branch for experiments)\nclaude-code-skill session-fork myproject myproject-experiment\n\n# Stop\nclaude-code-skill session-stop myproject\n\n# Restart a failed session\nclaude-code-skill session-restart myproject"
      },
      {
        "title": "Session History & Search",
        "body": "# Browse all Claude Code sessions\nclaude-code-skill sessions -n 20\n\n# Search sessions by project\nclaude-code-skill session-search --project ~/myapp\n\n# Search by time\nclaude-code-skill session-search --since \"2h\"\nclaude-code-skill session-search --since \"2024-02-01\"\n\n# Search by query\nclaude-code-skill session-search \"bug fix\"\n\n# Resume a historical session\nclaude-code-skill resume <session-id> \"Continue where we left off\" -d ~/project"
      },
      {
        "title": "Batch Operations",
        "body": "# Read multiple files at once\nclaude-code-skill batch-read \"src/**/*.ts\" \"tests/**/*.test.ts\" -p ~/project"
      },
      {
        "title": "🤝 Agent Team Features",
        "body": "Deploy multiple Claude agents working together on complex tasks."
      },
      {
        "title": "Basic Agent Team",
        "body": "# Define a team of agents\nclaude-code-skill session-start team-project -d ~/project \\\n  --agents '{\n    \"architect\": {\n      \"description\": \"Designs system architecture\",\n      \"prompt\": \"You are a senior software architect. Design scalable, maintainable systems.\"\n    },\n    \"developer\": {\n      \"description\": \"Implements features\",\n      \"prompt\": \"You are a full-stack developer. Write clean, tested code.\"\n    },\n    \"reviewer\": {\n      \"description\": \"Reviews code quality\",\n      \"prompt\": \"You are a code reviewer. Check for bugs, style issues, and improvements.\"\n    }\n  }' \\\n  --agent architect\n\n# Switch between agents mid-conversation\nclaude-code-skill session-send team-project \"Design the authentication system\"\n# (architect responds)\n\nclaude-code-skill session-send team-project \"@developer implement the design\"\n# (developer agent takes over)\n\nclaude-code-skill session-send team-project \"@reviewer review the implementation\"\n# (reviewer agent takes over)"
      },
      {
        "title": "Pre-configured Team Templates",
        "body": "# Code review team\nclaude-code-skill session-start review -d ~/project \\\n  --agents '{\n    \"security\": {\"prompt\": \"Focus on security vulnerabilities\"},\n    \"performance\": {\"prompt\": \"Focus on performance issues\"},\n    \"quality\": {\"prompt\": \"Focus on code quality and maintainability\"}\n  }' \\\n  --agent security\n\n# Full-stack team\nclaude-code-skill session-start fullstack -d ~/project \\\n  --agents '{\n    \"frontend\": {\"prompt\": \"React/TypeScript frontend specialist\"},\n    \"backend\": {\"prompt\": \"Node.js/Express backend specialist\"},\n    \"database\": {\"prompt\": \"PostgreSQL/Redis database specialist\"}\n  }' \\\n  --agent frontend"
      },
      {
        "title": "Tool Control",
        "body": "# Allow specific tools with patterns\n--allowed-tools \"Bash(git:*,npm:*),Read,Edit\"\n\n# Deny dangerous operations\n--disallowed-tools \"Bash(rm:*,sudo:*),Write(/etc/*)\"\n\n# Limit to specific tool set\n--tools \"Read,Glob,Grep\"\n\n# Disable all tools\n--tools \"\""
      },
      {
        "title": "System Prompts",
        "body": "# Replace system prompt completely\n--system-prompt \"You are a Python expert. Always use type hints.\"\n\n# Append to existing prompt\n--append-system-prompt \"Always run tests after changes.\""
      },
      {
        "title": "Session Management",
        "body": "# Resume with fork (create a branch)\n--resume <session-id> --fork-session\n\n# Use custom UUID for session\n--session-id \"550e8400-e29b-41d4-a716-446655440000\"\n\n# Add additional working directories\n--add-dir \"/var/log,/tmp/workspace\""
      },
      {
        "title": "Multi-Model Support (Proxy)",
        "body": "Use --base-url to route requests through a proxy, enabling other models (Gemini, GPT) to power Claude Code:\n\n# Use Gemini via claude-code-proxy\nclaude-code-skill session-start gemini-task -d ~/project \\\n  --base-url http://127.0.0.1:8082 \\\n  --model claude-3-5-sonnet-20241022  # Proxy will map to Gemini\n\n# Use GPT via proxy\nclaude-code-skill session-start gpt-task -d ~/project \\\n  --base-url http://127.0.0.1:8082 \\\n  --model claude-3-haiku-20240307  # Proxy will map to GPT\n\nNote: Requires claude-code-proxy running on port 8082 with proper API keys configured.\n\n# Start the proxy\ncd ~/clawd/claude-code-proxy && source .venv/bin/activate\nuvicorn server:app --host 127.0.0.1 --port 8082"
      },
      {
        "title": "For OpenClaw Agents",
        "body": "Always use persistent sessions for multi-step tasks\n# ❌ Bad: Multiple disconnect/reconnect cycles\nclaude-code-skill bash \"step1\"\nclaude-code-skill bash \"step2\"\n\n# ✅ Good: Single persistent session\nclaude-code-skill session-start task -d ~/project\nclaude-code-skill session-send task \"Do step1 then step2\"\n\n\n\nUse --stream for long-running tasks\nclaude-code-skill session-send task \"Run full test suite\" --stream\n\n\n\nSet budget limits for safety\n--max-budget 2.00  # Stop after $2 of API usage\n\n\n\nUse plan mode for critical changes\n--permission-mode plan  # Preview before applying\n\n\n\nFork before experiments\nclaude-code-skill session-fork main experimental\nclaude-code-skill session-send experimental \"Try risky refactor\""
      },
      {
        "title": "Error Recovery",
        "body": "# If session fails:\nclaude-code-skill session-status myproject  # Check what happened\nclaude-code-skill session-history myproject -n 20  # See recent events\nclaude-code-skill session-restart myproject  # Restart from last good state\n\n# If you need to start over:\nclaude-code-skill session-stop myproject\nclaude-code-skill session-start myproject -d ~/project --resume <old-session-id>"
      },
      {
        "title": "🏗️ Architecture",
        "body": "openclaw agent\n    ↓\nclaude-code-skill CLI (this tool)\n    ↓ HTTP\nsasha-doctor API (:18795)\n    ↓ MCP\nclaude mcp serve (Claude Code)\n    ↓\nYour files & tools"
      },
      {
        "title": "🔌 Available Tools (via MCP)",
        "body": "All Claude Code tools are accessible:\n\nToolDescriptionBashExecute shell commandsReadRead file contentsWriteCreate/overwrite filesEditEdit files with string replacementGlobFind files by patternGrepSearch file contentsTaskLaunch sub-agentsWebFetchFetch web contentWebSearchSearch the webGit*Git operationsAskUserQuestionInteractive prompts...and 10+ more"
      },
      {
        "title": "Example 1: Code Review",
        "body": "claude-code-skill session-start review -d ~/myapp \\\n  --permission-mode plan \\\n  --agents '{\"security\":{\"prompt\":\"Focus on security\"},\"quality\":{\"prompt\":\"Focus on quality\"}}' \\\n  --agent security\n\nclaude-code-skill session-send review \\\n  \"Review all TypeScript files in src/, check for security issues and code quality problems\" \\\n  --stream"
      },
      {
        "title": "Example 2: Automated Testing",
        "body": "claude-code-skill session-start test -d ~/myapp \\\n  --allowed-tools \"Bash(npm:*,git:*),Read,Write\" \\\n  --max-budget 1.00\n\nclaude-code-skill session-send test \\\n  \"Find all untested functions, write unit tests, run tests, fix failures\""
      },
      {
        "title": "Example 3: Multi-Agent Debugging",
        "body": "claude-code-skill session-start debug -d ~/myapp \\\n  --agents '{\n    \"detective\": {\"prompt\": \"Find the root cause of bugs\"},\n    \"fixer\": {\"prompt\": \"Implement fixes\"},\n    \"tester\": {\"prompt\": \"Verify fixes work\"}\n  }' \\\n  --agent detective\n\nclaude-code-skill session-send debug \"We have a memory leak in the API server\" --stream\n# Detective investigates, then hands off to fixer, then to tester"
      },
      {
        "title": "🔗 Integration with OpenClaw",
        "body": "When openclaw needs to perform complex coding tasks:\n\n# From within openclaw agent context:\nopenclaw skills run claude-code-skill -- session-start task -d ~/project\nopenclaw skills run claude-code-skill -- session-send task \"Implement feature X\" --stream\nopenclaw skills run claude-code-skill -- session-status task\n\nOr use the skill programmatically via sasha-doctor HTTP API (see TOOLS.md section 3)."
      },
      {
        "title": "📖 See Also",
        "body": "TOOLS.md section 3 - Full HTTP API documentation\nsasha-doctor endpoints - Backend integration details\nClaude Code docs - Official Claude Code documentation (query via qmd tool)"
      }
    ],
    "body": "Claude Code Skill\n\nControl Claude Code via MCP (Model Context Protocol). This skill unleashes the full power of Claude Code for openclaw agents, including persistent sessions, agent teams, and advanced tool control.\n\n⚡ Quick Start\n# Start a persistent Claude session for your project\nclaude-code-skill session-start myproject -d ~/project \\\n  --permission-mode plan \\\n  --allowed-tools \"Bash,Read,Edit,Write,Glob,Grep\" \\\n  --max-budget 2.00\n\n# Send a complex task (Claude will autonomously use tools)\nclaude-code-skill session-send myproject \"Find all TODO comments and create GitHub issues\" --stream\n\n# Check progress\nclaude-code-skill session-status myproject\n\n🎯 When to Use This Skill\nUse Persistent Sessions When:\n✅ Multi-step tasks requiring multiple tool calls\n✅ Iterative development (write code → test → fix → repeat)\n✅ Long conversations needing full context\n✅ Agent needs to work autonomously\n✅ You want streaming real-time feedback\nUse Direct MCP Tools When:\n✅ Single command execution\n✅ Quick file read/write\n✅ One-off searches\n✅ No context needed between operations\n📚 Command Reference\nBasic MCP Operations\n# Connect to Claude Code MCP\nclaude-code-skill connect\nclaude-code-skill status\nclaude-code-skill tools\n\n# Direct tool calls (no persistent session)\nclaude-code-skill bash \"npm test\"\nclaude-code-skill read /path/to/file.ts\nclaude-code-skill glob \"**/*.ts\" -p ~/project\nclaude-code-skill grep \"TODO\" -p ~/project -c\nclaude-code-skill call Write -a '{\"file_path\":\"/tmp/test.txt\",\"content\":\"Hello\"}'\n\n# Disconnect\nclaude-code-skill disconnect\n\nPersistent Sessions (Agent Loop)\nStarting Sessions\n# Basic start\nclaude-code-skill session-start myproject -d ~/project\n\n# With custom API endpoint (for Gemini/GPT proxy)\nclaude-code-skill session-start gemini-task -d ~/project \\\n  --base-url http://127.0.0.1:8082 \\\n  --model gemini-2.0-flash\n\n# With permission mode (plan = preview changes before applying)\nclaude-code-skill session-start review -d ~/project --permission-mode plan\n\n# With tool whitelist (auto-approve these tools)\nclaude-code-skill session-start safe -d ~/project \\\n  --allowed-tools \"Bash(git:*),Read,Glob,Grep\"\n\n# With budget limit\nclaude-code-skill session-start limited -d ~/project --max-budget 1.50\n\n# Full configuration\nclaude-code-skill session-start advanced -d ~/project \\\n  --permission-mode acceptEdits \\\n  --allowed-tools \"Bash,Read,Edit,Write\" \\\n  --disallowed-tools \"Task\" \\\n  --max-budget 5.00 \\\n  --model claude-opus-4-5 \\\n  --append-system-prompt \"Always write tests\" \\\n  --add-dir \"/tmp,/var/log\"\n\n\nPermission Modes:\n\nMode\tDescription\nacceptEdits\tAuto-accept file edits (default)\nplan\tPreview changes before applying\ndefault\tAsk for each operation\nbypassPermissions\tSkip all prompts (dangerous!)\ndelegate\tDelegate decisions to parent\ndontAsk\tNever ask, reject by default\nSending Messages\n# Basic send (blocks until complete)\nclaude-code-skill session-send myproject \"Write unit tests for auth.ts\"\n\n# Streaming (see progress in real-time)\nclaude-code-skill session-send myproject \"Refactor this module\" --stream\n\n# With custom timeout\nclaude-code-skill session-send myproject \"Run all tests\" -t 300000\n\nManaging Sessions\n# List active sessions\nclaude-code-skill session-list\n\n# Get detailed status\nclaude-code-skill session-status myproject\n\n# View conversation history\nclaude-code-skill session-history myproject -n 50\n\n# Pause and resume\nclaude-code-skill session-pause myproject\nclaude-code-skill session-resume-paused myproject\n\n# Fork a session (create a branch for experiments)\nclaude-code-skill session-fork myproject myproject-experiment\n\n# Stop\nclaude-code-skill session-stop myproject\n\n# Restart a failed session\nclaude-code-skill session-restart myproject\n\nSession History & Search\n# Browse all Claude Code sessions\nclaude-code-skill sessions -n 20\n\n# Search sessions by project\nclaude-code-skill session-search --project ~/myapp\n\n# Search by time\nclaude-code-skill session-search --since \"2h\"\nclaude-code-skill session-search --since \"2024-02-01\"\n\n# Search by query\nclaude-code-skill session-search \"bug fix\"\n\n# Resume a historical session\nclaude-code-skill resume <session-id> \"Continue where we left off\" -d ~/project\n\nBatch Operations\n# Read multiple files at once\nclaude-code-skill batch-read \"src/**/*.ts\" \"tests/**/*.test.ts\" -p ~/project\n\n🤝 Agent Team Features\n\nDeploy multiple Claude agents working together on complex tasks.\n\nBasic Agent Team\n# Define a team of agents\nclaude-code-skill session-start team-project -d ~/project \\\n  --agents '{\n    \"architect\": {\n      \"description\": \"Designs system architecture\",\n      \"prompt\": \"You are a senior software architect. Design scalable, maintainable systems.\"\n    },\n    \"developer\": {\n      \"description\": \"Implements features\",\n      \"prompt\": \"You are a full-stack developer. Write clean, tested code.\"\n    },\n    \"reviewer\": {\n      \"description\": \"Reviews code quality\",\n      \"prompt\": \"You are a code reviewer. Check for bugs, style issues, and improvements.\"\n    }\n  }' \\\n  --agent architect\n\n# Switch between agents mid-conversation\nclaude-code-skill session-send team-project \"Design the authentication system\"\n# (architect responds)\n\nclaude-code-skill session-send team-project \"@developer implement the design\"\n# (developer agent takes over)\n\nclaude-code-skill session-send team-project \"@reviewer review the implementation\"\n# (reviewer agent takes over)\n\nPre-configured Team Templates\n# Code review team\nclaude-code-skill session-start review -d ~/project \\\n  --agents '{\n    \"security\": {\"prompt\": \"Focus on security vulnerabilities\"},\n    \"performance\": {\"prompt\": \"Focus on performance issues\"},\n    \"quality\": {\"prompt\": \"Focus on code quality and maintainability\"}\n  }' \\\n  --agent security\n\n# Full-stack team\nclaude-code-skill session-start fullstack -d ~/project \\\n  --agents '{\n    \"frontend\": {\"prompt\": \"React/TypeScript frontend specialist\"},\n    \"backend\": {\"prompt\": \"Node.js/Express backend specialist\"},\n    \"database\": {\"prompt\": \"PostgreSQL/Redis database specialist\"}\n  }' \\\n  --agent frontend\n\n🔧 Advanced Features\nTool Control\n# Allow specific tools with patterns\n--allowed-tools \"Bash(git:*,npm:*),Read,Edit\"\n\n# Deny dangerous operations\n--disallowed-tools \"Bash(rm:*,sudo:*),Write(/etc/*)\"\n\n# Limit to specific tool set\n--tools \"Read,Glob,Grep\"\n\n# Disable all tools\n--tools \"\"\n\nSystem Prompts\n# Replace system prompt completely\n--system-prompt \"You are a Python expert. Always use type hints.\"\n\n# Append to existing prompt\n--append-system-prompt \"Always run tests after changes.\"\n\nSession Management\n# Resume with fork (create a branch)\n--resume <session-id> --fork-session\n\n# Use custom UUID for session\n--session-id \"550e8400-e29b-41d4-a716-446655440000\"\n\n# Add additional working directories\n--add-dir \"/var/log,/tmp/workspace\"\n\nMulti-Model Support (Proxy)\n\nUse --base-url to route requests through a proxy, enabling other models (Gemini, GPT) to power Claude Code:\n\n# Use Gemini via claude-code-proxy\nclaude-code-skill session-start gemini-task -d ~/project \\\n  --base-url http://127.0.0.1:8082 \\\n  --model claude-3-5-sonnet-20241022  # Proxy will map to Gemini\n\n# Use GPT via proxy\nclaude-code-skill session-start gpt-task -d ~/project \\\n  --base-url http://127.0.0.1:8082 \\\n  --model claude-3-haiku-20240307  # Proxy will map to GPT\n\n\nNote: Requires claude-code-proxy running on port 8082 with proper API keys configured.\n\n# Start the proxy\ncd ~/clawd/claude-code-proxy && source .venv/bin/activate\nuvicorn server:app --host 127.0.0.1 --port 8082\n\n🎓 Best Practices\nFor OpenClaw Agents\n\nAlways use persistent sessions for multi-step tasks\n\n# ❌ Bad: Multiple disconnect/reconnect cycles\nclaude-code-skill bash \"step1\"\nclaude-code-skill bash \"step2\"\n\n# ✅ Good: Single persistent session\nclaude-code-skill session-start task -d ~/project\nclaude-code-skill session-send task \"Do step1 then step2\"\n\n\nUse --stream for long-running tasks\n\nclaude-code-skill session-send task \"Run full test suite\" --stream\n\n\nSet budget limits for safety\n\n--max-budget 2.00  # Stop after $2 of API usage\n\n\nUse plan mode for critical changes\n\n--permission-mode plan  # Preview before applying\n\n\nFork before experiments\n\nclaude-code-skill session-fork main experimental\nclaude-code-skill session-send experimental \"Try risky refactor\"\n\nError Recovery\n# If session fails:\nclaude-code-skill session-status myproject  # Check what happened\nclaude-code-skill session-history myproject -n 20  # See recent events\nclaude-code-skill session-restart myproject  # Restart from last good state\n\n# If you need to start over:\nclaude-code-skill session-stop myproject\nclaude-code-skill session-start myproject -d ~/project --resume <old-session-id>\n\n🏗️ Architecture\nopenclaw agent\n    ↓\nclaude-code-skill CLI (this tool)\n    ↓ HTTP\nsasha-doctor API (:18795)\n    ↓ MCP\nclaude mcp serve (Claude Code)\n    ↓\nYour files & tools\n\n🔌 Available Tools (via MCP)\n\nAll Claude Code tools are accessible:\n\nTool\tDescription\nBash\tExecute shell commands\nRead\tRead file contents\nWrite\tCreate/overwrite files\nEdit\tEdit files with string replacement\nGlob\tFind files by pattern\nGrep\tSearch file contents\nTask\tLaunch sub-agents\nWebFetch\tFetch web content\nWebSearch\tSearch the web\nGit*\tGit operations\nAskUserQuestion\tInteractive prompts\n...\tand 10+ more\n📊 Examples\nExample 1: Code Review\nclaude-code-skill session-start review -d ~/myapp \\\n  --permission-mode plan \\\n  --agents '{\"security\":{\"prompt\":\"Focus on security\"},\"quality\":{\"prompt\":\"Focus on quality\"}}' \\\n  --agent security\n\nclaude-code-skill session-send review \\\n  \"Review all TypeScript files in src/, check for security issues and code quality problems\" \\\n  --stream\n\nExample 2: Automated Testing\nclaude-code-skill session-start test -d ~/myapp \\\n  --allowed-tools \"Bash(npm:*,git:*),Read,Write\" \\\n  --max-budget 1.00\n\nclaude-code-skill session-send test \\\n  \"Find all untested functions, write unit tests, run tests, fix failures\"\n\nExample 3: Multi-Agent Debugging\nclaude-code-skill session-start debug -d ~/myapp \\\n  --agents '{\n    \"detective\": {\"prompt\": \"Find the root cause of bugs\"},\n    \"fixer\": {\"prompt\": \"Implement fixes\"},\n    \"tester\": {\"prompt\": \"Verify fixes work\"}\n  }' \\\n  --agent detective\n\nclaude-code-skill session-send debug \"We have a memory leak in the API server\" --stream\n# Detective investigates, then hands off to fixer, then to tester\n\n🔗 Integration with OpenClaw\n\nWhen openclaw needs to perform complex coding tasks:\n\n# From within openclaw agent context:\nopenclaw skills run claude-code-skill -- session-start task -d ~/project\nopenclaw skills run claude-code-skill -- session-send task \"Implement feature X\" --stream\nopenclaw skills run claude-code-skill -- session-status task\n\n\nOr use the skill programmatically via sasha-doctor HTTP API (see TOOLS.md section 3).\n\n📖 See Also\nTOOLS.md section 3 - Full HTTP API documentation\nsasha-doctor endpoints - Backend integration details\nClaude Code docs - Official Claude Code documentation (query via qmd tool)"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Enderfga/openclaw-claude-code",
    "publisherUrl": "https://clawhub.ai/Enderfga/openclaw-claude-code",
    "owner": "Enderfga",
    "version": "0.3.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/openclaw-claude-code",
    "downloadUrl": "https://openagent3.xyz/downloads/openclaw-claude-code",
    "agentUrl": "https://openagent3.xyz/skills/openclaw-claude-code/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-claude-code/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-claude-code/agent.md"
  }
}