{
  "schemaVersion": "1.0",
  "item": {
    "slug": "tmux-agents",
    "name": "Tmux Agents",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/cuba6112/tmux-agents",
    "canonicalUrl": "https://clawhub.ai/cuba6112/tmux-agents",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/tmux-agents",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=tmux-agents",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "scripts/check.sh",
      "scripts/spawn.sh",
      "scripts/status.sh"
    ],
    "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/tmux-agents"
    },
    "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/tmux-agents",
    "agentPageUrl": "https://openagent3.xyz/skills/tmux-agents/agent",
    "manifestUrl": "https://openagent3.xyz/skills/tmux-agents/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/tmux-agents/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": "Tmux Agents",
        "body": "Run coding agents in persistent tmux sessions. They work in the background while you do other things."
      },
      {
        "title": "☁️ Cloud Agents (API credits)",
        "body": "AgentCommandBest ForclaudeClaude CodeComplex coding, refactoring, full projectscodexOpenAI CodexQuick edits, auto-approve modegeminiGoogle GeminiResearch, analysis, documentation"
      },
      {
        "title": "🦙 Local Agents (FREE via Ollama)",
        "body": "AgentCommandBest Forollama-claudeClaude Code + OllamaLong experiments, heavy refactoringollama-codexCodex + OllamaExtended coding sessions\n\nLocal agents use your Mac's GPU — no API costs, great for experimentation!"
      },
      {
        "title": "Spawn a new agent session",
        "body": "./skills/tmux-agents/scripts/spawn.sh <name> <task> [agent]\n\n# Cloud (uses API credits)\n./skills/tmux-agents/scripts/spawn.sh fix-bug \"Fix login validation\" claude\n./skills/tmux-agents/scripts/spawn.sh refactor \"Refactor the auth module\" codex\n./skills/tmux-agents/scripts/spawn.sh research \"Research caching strategies\" gemini\n\n# Local (FREE - uses Ollama)\n./skills/tmux-agents/scripts/spawn.sh experiment \"Rewrite entire test suite\" ollama-claude\n./skills/tmux-agents/scripts/spawn.sh big-refactor \"Refactor all services\" ollama-codex"
      },
      {
        "title": "List running sessions",
        "body": "tmux list-sessions\n# or\n./skills/tmux-agents/scripts/status.sh"
      },
      {
        "title": "Check on a session",
        "body": "./skills/tmux-agents/scripts/check.sh session-name"
      },
      {
        "title": "Attach to watch live",
        "body": "tmux attach -t session-name\n# Detach with: Ctrl+B, then D"
      },
      {
        "title": "Send additional instructions",
        "body": "tmux send-keys -t session-name \"additional instruction here\" Enter"
      },
      {
        "title": "Kill a session when done",
        "body": "tmux kill-session -t session-name"
      },
      {
        "title": "When to Use Local vs Cloud",
        "body": "ScenarioRecommendationQuick fix, time-sensitive☁️ Cloud (faster)Expensive task, budget matters🦙 LocalLong experiment, might fail🦙 LocalProduction code review☁️ Cloud (smarter)Learning/exploring🦙 LocalHeavy refactoring🦙 Local"
      },
      {
        "title": "Parallel Agents",
        "body": "Run multiple agents simultaneously:\n\n# Mix and match cloud + local\n./scripts/spawn.sh backend \"Implement user API\" claude           # Cloud\n./scripts/spawn.sh frontend \"Build login form\" ollama-codex      # Local\n./scripts/spawn.sh docs \"Write API documentation\" gemini         # Cloud\n./scripts/spawn.sh tests \"Write all unit tests\" ollama-claude    # Local\n\nCheck all at once:\n\n./skills/tmux-agents/scripts/status.sh"
      },
      {
        "title": "Ollama Setup",
        "body": "Local agents require Ollama with a coding model:\n\n# Pull recommended model\nollama pull glm-4.7-flash\n\n# Configure tools (one-time)\nollama launch claude --model glm-4.7-flash --config\nollama launch codex --model glm-4.7-flash --config"
      },
      {
        "title": "Tips",
        "body": "Sessions persist even if Clawdbot restarts\nUse local agents for risky/experimental work\nUse cloud for production-critical tasks\nCheck tmux ls to see all active work\nKill sessions when done to free resources"
      }
    ],
    "body": "Tmux Agents\n\nRun coding agents in persistent tmux sessions. They work in the background while you do other things.\n\nAvailable Agents\n☁️ Cloud Agents (API credits)\nAgent\tCommand\tBest For\nclaude\tClaude Code\tComplex coding, refactoring, full projects\ncodex\tOpenAI Codex\tQuick edits, auto-approve mode\ngemini\tGoogle Gemini\tResearch, analysis, documentation\n🦙 Local Agents (FREE via Ollama)\nAgent\tCommand\tBest For\nollama-claude\tClaude Code + Ollama\tLong experiments, heavy refactoring\nollama-codex\tCodex + Ollama\tExtended coding sessions\n\nLocal agents use your Mac's GPU — no API costs, great for experimentation!\n\nQuick Commands\nSpawn a new agent session\n./skills/tmux-agents/scripts/spawn.sh <name> <task> [agent]\n\n# Cloud (uses API credits)\n./skills/tmux-agents/scripts/spawn.sh fix-bug \"Fix login validation\" claude\n./skills/tmux-agents/scripts/spawn.sh refactor \"Refactor the auth module\" codex\n./skills/tmux-agents/scripts/spawn.sh research \"Research caching strategies\" gemini\n\n# Local (FREE - uses Ollama)\n./skills/tmux-agents/scripts/spawn.sh experiment \"Rewrite entire test suite\" ollama-claude\n./skills/tmux-agents/scripts/spawn.sh big-refactor \"Refactor all services\" ollama-codex\n\nList running sessions\ntmux list-sessions\n# or\n./skills/tmux-agents/scripts/status.sh\n\nCheck on a session\n./skills/tmux-agents/scripts/check.sh session-name\n\nAttach to watch live\ntmux attach -t session-name\n# Detach with: Ctrl+B, then D\n\nSend additional instructions\ntmux send-keys -t session-name \"additional instruction here\" Enter\n\nKill a session when done\ntmux kill-session -t session-name\n\nWhen to Use Local vs Cloud\nScenario\tRecommendation\nQuick fix, time-sensitive\t☁️ Cloud (faster)\nExpensive task, budget matters\t🦙 Local\nLong experiment, might fail\t🦙 Local\nProduction code review\t☁️ Cloud (smarter)\nLearning/exploring\t🦙 Local\nHeavy refactoring\t🦙 Local\nParallel Agents\n\nRun multiple agents simultaneously:\n\n# Mix and match cloud + local\n./scripts/spawn.sh backend \"Implement user API\" claude           # Cloud\n./scripts/spawn.sh frontend \"Build login form\" ollama-codex      # Local\n./scripts/spawn.sh docs \"Write API documentation\" gemini         # Cloud\n./scripts/spawn.sh tests \"Write all unit tests\" ollama-claude    # Local\n\n\nCheck all at once:\n\n./skills/tmux-agents/scripts/status.sh\n\nOllama Setup\n\nLocal agents require Ollama with a coding model:\n\n# Pull recommended model\nollama pull glm-4.7-flash\n\n# Configure tools (one-time)\nollama launch claude --model glm-4.7-flash --config\nollama launch codex --model glm-4.7-flash --config\n\nTips\nSessions persist even if Clawdbot restarts\nUse local agents for risky/experimental work\nUse cloud for production-critical tasks\nCheck tmux ls to see all active work\nKill sessions when done to free resources"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/cuba6112/tmux-agents",
    "publisherUrl": "https://clawhub.ai/cuba6112/tmux-agents",
    "owner": "cuba6112",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/tmux-agents",
    "downloadUrl": "https://openagent3.xyz/downloads/tmux-agents",
    "agentUrl": "https://openagent3.xyz/skills/tmux-agents/agent",
    "manifestUrl": "https://openagent3.xyz/skills/tmux-agents/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/tmux-agents/agent.md"
  }
}