{
  "schemaVersion": "1.0",
  "item": {
    "slug": "claude-tmux",
    "name": "Claude Code within tmux",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/paulrahul/claude-tmux",
    "canonicalUrl": "https://clawhub.ai/paulrahul/claude-tmux",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/claude-tmux",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=claude-tmux",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "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. 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. 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/claude-tmux"
    },
    "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/claude-tmux",
    "agentPageUrl": "https://openagent3.xyz/skills/claude-tmux/agent",
    "manifestUrl": "https://openagent3.xyz/skills/claude-tmux/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/claude-tmux/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. 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. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Goal",
        "body": "Give Codex a repeatable checklist for interacting with Claude Code when it’s running inside tmux. Everything happens with standard tmux commands—no helper scripts. Follow these steps any time you see instructions like “check Claude in session X” or “run /compact on Claude.”"
      },
      {
        "title": "Conventions",
        "body": "Session naming – We refer to tmux sessions by their tmux session name. Session names can be assigned using tmux new-session -s <session_name>. E.g. if we had created a tmux session for project FooBar using tmux new-session -s foobar, then we will refer to this session by the name foobar.\nClaude pane – Within a session, there should be exactly one pane whose window title or pane title is claude. If the pane isn’t named, rename it first (Ctrl-b : select-pane -T claude).\nStandard markers – Claude Code prints user prompts with ❯ … and its replies with ⏺ …. We rely on that to spot the latest exchange."
      },
      {
        "title": "1. Locate the Claude pane",
        "body": "tmux list-panes -a -F '#{session_name}:#{window_index}.#{pane_index} #{pane_title}' | grep \"^<session_name>\" | grep -i claude\n\nIf nothing matches, say “No pane titled ‘claude’ found inside session <name>.”\nIf multiple panes match, pick the one with the lowest window_index/pane_index unless context says otherwise.\nRecord the target as <session>:<window>.<pane> for subsequent commands."
      },
      {
        "title": "2. View the latest exchange",
        "body": "tmux capture-pane -p -J -t <target> -S -200\n\nScan from the bottom upward for the last ❯ block (user) followed by ⏺ (Claude). Quote those lines back to the user.\nIf no ❯/⏺ pair exists, say “No exchange found yet.”"
      },
      {
        "title": "3. Send a prompt",
        "body": "tmux send-keys -t <target> -l -- \"<prompt>\"\nsleep 0.1\n tmux send-keys -t <target> Enter\n\nAfter sending, poll using capture-pane until a new ⏺ block appears (or a sensible timeout, e.g., 3 minutes). Report the reply verbatim.\nIf the timeout expires, say “Claude hasn’t replied yet—still waiting.”"
      },
      {
        "title": "4. Run /compact",
        "body": "Same as sending any prompt, but send /compact. Confirm with “Triggered /compact in session <name>.” (Claude will respond in-pane; no need to quote unless asked.)"
      },
      {
        "title": "5. Dump raw buffer (debug)",
        "body": "tmux capture-pane -p -J -t <target> -S -400\n\nUse this when the user wants the entire scrollback or when parsing fails."
      },
      {
        "title": "Tips",
        "body": "Always double-check you’re addressing the right pane before sending commands—especially in shared sessions.\nIf the Claude pane lives on a non-default tmux socket, prefix every tmux command with tmux -S /path/to/socket ….\nWhen summarizing results, mention the session/pane you used—for traceability.\nIf the user wants multiple sessions handled, repeat the workflow per session.\n\nThis skill keeps things simple: pure tmux, no external code. Use it whenever you need hands-on access to Claude Code running inside tmux."
      }
    ],
    "body": "Goal\n\nGive Codex a repeatable checklist for interacting with Claude Code when it’s running inside tmux. Everything happens with standard tmux commands—no helper scripts. Follow these steps any time you see instructions like “check Claude in session X” or “run /compact on Claude.”\n\nConventions\nSession naming – We refer to tmux sessions by their tmux session name. Session names can be assigned using tmux new-session -s <session_name>. E.g. if we had created a tmux session for project FooBar using tmux new-session -s foobar, then we will refer to this session by the name foobar.\nClaude pane – Within a session, there should be exactly one pane whose window title or pane title is claude. If the pane isn’t named, rename it first (Ctrl-b : select-pane -T claude).\nStandard markers – Claude Code prints user prompts with ❯ … and its replies with ⏺ …. We rely on that to spot the latest exchange.\nWorkflow\n1. Locate the Claude pane\ntmux list-panes -a -F '#{session_name}:#{window_index}.#{pane_index} #{pane_title}' | grep \"^<session_name>\" | grep -i claude\n\nIf nothing matches, say “No pane titled ‘claude’ found inside session <name>.”\nIf multiple panes match, pick the one with the lowest window_index/pane_index unless context says otherwise.\nRecord the target as <session>:<window>.<pane> for subsequent commands.\n2. View the latest exchange\ntmux capture-pane -p -J -t <target> -S -200\n\nScan from the bottom upward for the last ❯ block (user) followed by ⏺ (Claude). Quote those lines back to the user.\nIf no ❯/⏺ pair exists, say “No exchange found yet.”\n3. Send a prompt\ntmux send-keys -t <target> -l -- \"<prompt>\"\nsleep 0.1\n tmux send-keys -t <target> Enter\n\nAfter sending, poll using capture-pane until a new ⏺ block appears (or a sensible timeout, e.g., 3 minutes). Report the reply verbatim.\nIf the timeout expires, say “Claude hasn’t replied yet—still waiting.”\n4. Run /compact\n\nSame as sending any prompt, but send /compact. Confirm with “Triggered /compact in session <name>.” (Claude will respond in-pane; no need to quote unless asked.)\n\n5. Dump raw buffer (debug)\ntmux capture-pane -p -J -t <target> -S -400\n\n\nUse this when the user wants the entire scrollback or when parsing fails.\n\nTips\nAlways double-check you’re addressing the right pane before sending commands—especially in shared sessions.\nIf the Claude pane lives on a non-default tmux socket, prefix every tmux command with tmux -S /path/to/socket ….\nWhen summarizing results, mention the session/pane you used—for traceability.\nIf the user wants multiple sessions handled, repeat the workflow per session.\n\nThis skill keeps things simple: pure tmux, no external code. Use it whenever you need hands-on access to Claude Code running inside tmux."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/paulrahul/claude-tmux",
    "publisherUrl": "https://clawhub.ai/paulrahul/claude-tmux",
    "owner": "paulrahul",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/claude-tmux",
    "downloadUrl": "https://openagent3.xyz/downloads/claude-tmux",
    "agentUrl": "https://openagent3.xyz/skills/claude-tmux/agent",
    "manifestUrl": "https://openagent3.xyz/skills/claude-tmux/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/claude-tmux/agent.md"
  }
}