{
  "schemaVersion": "1.0",
  "item": {
    "slug": "session-watchdog",
    "name": "Session Watchdog",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/xbillwatsonx/session-watchdog",
    "canonicalUrl": "https://clawhub.ai/xbillwatsonx/session-watchdog",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/session-watchdog",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=session-watchdog",
    "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/session-watchdog"
    },
    "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/session-watchdog",
    "agentPageUrl": "https://openagent3.xyz/skills/session-watchdog/agent",
    "manifestUrl": "https://openagent3.xyz/skills/session-watchdog/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/session-watchdog/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": "Session Watchdog",
        "body": "Monitors context levels, warns before compaction, and saves checkpoints to preserve important information."
      },
      {
        "title": "Context Thresholds",
        "body": "LevelTokensActionSafe0-140kNormal operationWarning140k-160kWarn user, save checkpointCritical160k-197kWarn + stop unless urgentFull197k+Compaction imminent"
      },
      {
        "title": "Check Context",
        "body": "Before each session and periodically during long conversations:\n\nsession_status\n\nCheck the contextTokens field from the response."
      },
      {
        "title": "Checkpoint Protocol",
        "body": "When approaching 80% (160k tokens):\n\nSave checkpoint to memory file:\n\nRead current memory/YYYY-MM-DD.md\nAdd key context: decisions, pending tasks, important details\nWrite back to memory file\n\n\n\nAlert user:\nSay: \"⚠️ Approaching context limit (~160k tokens). Saving checkpoint to memory before continuing.\"\n\n\nAsk user:\n\nContinue and accept compaction?\nSummarize and restart fresh?\nPause until ready?"
      },
      {
        "title": "What to Save",
        "body": "Essential information that must survive compaction:\n\nDecisions made in this conversation\nPending tasks not yet completed\nImportant context (project state, configurations, preferences)\nFiles modified and their paths\nUnresolved issues requiring follow-up"
      },
      {
        "title": "When to Trigger",
        "body": "At session start\nAfter every 30k tokens of conversation\nBefore initiating large tasks (file edits, multiple operations)\nWhen user asks \"how much context do we have left?\""
      },
      {
        "title": "Memory File Format",
        "body": "# YYYY-MM-DD\n\n## Session Checkpoint (at X% context)\n\n### Decisions\n- Decision 1\n- Decision 2\n\n### Pending\n- [ ] Task 1\n- [ ] Task 2\n\n### Important Context\n- Project state: ...\n- Last file modified: ...\n\n### Unresolved\n- Issue needing follow-up"
      }
    ],
    "body": "Session Watchdog\n\nMonitors context levels, warns before compaction, and saves checkpoints to preserve important information.\n\nContext Thresholds\nLevel\tTokens\tAction\nSafe\t0-140k\tNormal operation\nWarning\t140k-160k\tWarn user, save checkpoint\nCritical\t160k-197k\tWarn + stop unless urgent\nFull\t197k+\tCompaction imminent\nCheck Context\n\nBefore each session and periodically during long conversations:\n\nsession_status\n\n\nCheck the contextTokens field from the response.\n\nCheckpoint Protocol\n\nWhen approaching 80% (160k tokens):\n\nSave checkpoint to memory file:\n\nRead current memory/YYYY-MM-DD.md\nAdd key context: decisions, pending tasks, important details\nWrite back to memory file\n\nAlert user: Say: \"⚠️ Approaching context limit (~160k tokens). Saving checkpoint to memory before continuing.\"\n\nAsk user:\n\nContinue and accept compaction?\nSummarize and restart fresh?\nPause until ready?\nWhat to Save\n\nEssential information that must survive compaction:\n\nDecisions made in this conversation\nPending tasks not yet completed\nImportant context (project state, configurations, preferences)\nFiles modified and their paths\nUnresolved issues requiring follow-up\nWhen to Trigger\nAt session start\nAfter every 30k tokens of conversation\nBefore initiating large tasks (file edits, multiple operations)\nWhen user asks \"how much context do we have left?\"\nMemory File Format\n# YYYY-MM-DD\n\n## Session Checkpoint (at X% context)\n\n### Decisions\n- Decision 1\n- Decision 2\n\n### Pending\n- [ ] Task 1\n- [ ] Task 2\n\n### Important Context\n- Project state: ...\n- Last file modified: ...\n\n### Unresolved\n- Issue needing follow-up"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/xbillwatsonx/session-watchdog",
    "publisherUrl": "https://clawhub.ai/xbillwatsonx/session-watchdog",
    "owner": "xbillwatsonx",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/session-watchdog",
    "downloadUrl": "https://openagent3.xyz/downloads/session-watchdog",
    "agentUrl": "https://openagent3.xyz/skills/session-watchdog/agent",
    "manifestUrl": "https://openagent3.xyz/skills/session-watchdog/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/session-watchdog/agent.md"
  }
}