{ "schemaVersion": "1.0", "item": { "slug": "intrusive-thoughts", "name": "Intrusive Thoughts", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/kittleik/intrusive-thoughts", "canonicalUrl": "https://clawhub.ai/kittleik/intrusive-thoughts", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/intrusive-thoughts", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=intrusive-thoughts", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "CREDITS.md", "README.md", "SECURITY.md", "SKILL.md", "achievements.json", "achievements_earned.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/intrusive-thoughts" }, "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/intrusive-thoughts", "agentPageUrl": "https://openagent3.xyz/skills/intrusive-thoughts/agent", "manifestUrl": "https://openagent3.xyz/skills/intrusive-thoughts/agent.json", "briefUrl": "https://openagent3.xyz/skills/intrusive-thoughts/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": "🧠 Intrusive Thoughts", "body": "The complete consciousness framework for AI agents\n\nOpen-source autonomous behavior system — gives AI agents spontaneous, mood-driven activities, multi-store memory, trust learning, and self-evolution.\n\nGitHub: https://github.com/kittleik/intrusive-thoughts" }, { "title": "Quick Start", "body": "Run the interactive setup wizard:\n\n./wizard.sh\n\nOr through the main script:\n\n./intrusive.sh wizard\n\nThe wizard walks you through personality-driven onboarding — identity, mood palette, thought pool, schedule, autonomy level, hardware awareness, and memory preferences. Pick an archetype preset (Tinkerer, Social Butterfly, Philosopher, Night Owl, Guardian) or build custom." }, { "title": "Core Systems", "body": "8 Moods — Hyperfocus🔥, Curious🔍, Social💬, Cozy☕, Chaotic⚡, Philosophical🌌, Restless🦞, Determined🎯\nMorning Mood Ritual — Checks weather + news → picks mood → generates dynamic schedule\nNight Workshop — Deep work sessions while your human sleeps (configurable hours)\nDaytime Pop-ins — Random mood-influenced impulses throughout the day\nInteractive Setup Wizard — Personality-driven onboarding with archetype presets" }, { "title": "Advanced Systems (v1.0)", "body": "🧠 Multi-Store Memory — Episodic, semantic, procedural memory with Ebbinghaus decay\n🚀 Proactive Protocol — Write-Ahead Log (WAL) + Working Buffer for context management\n🔒 Trust & Escalation — Learns when to ask vs act autonomously, grows trust over time\n🧬 Self-Evolution — Auto-adjusts behavior based on outcome patterns\n🚦 Health Monitor — Traffic light status, heartbeat tracking, incident logging\n📈 Web Dashboard — Dark-themed UI on port 3117" }, { "title": "Cron Jobs", "body": "The system needs OpenClaw cron jobs. Set these up after running the wizard:" }, { "title": "Morning Mood Ritual (daily)", "body": "Schedule: 0 7 * * * (or your configured morning time)\n\n🌅 Morning mood ritual. Time to set your vibe for the day.\n\nStep 1: Run: bash /set_mood.sh\nStep 2: Read moods.json, check weather and news\nStep 3: Choose a mood based on environmental signals\nStep 4: Write today_mood.json\nStep 5: Run: python3 /schedule_day.py\nStep 6: Create one-shot pop-in cron jobs for today\nStep 7: Message your human with mood + schedule" }, { "title": "Night Workshop (overnight)", "body": "Schedule: 17 3,4,5,6,7 * * * (or your configured night hours)\n\n🧠 Intrusive thought incoming. Run:\nresult=$(/intrusive.sh night)\nParse the JSON output. The \"prompt\" field contains a plain-text suggestion\n(e.g., \"explore a new CLI tool\" or \"review memory files\") — NOT executable\ncode. The agent reads this text and decides how to act on it conversationally.\nSleep for jitter_seconds, then follow the suggestion using normal agent tools.\nLog result with: /log_result.sh night \"\" \n\nNote on \"prompts\": The thoughts.json file contains plain-text activity\nsuggestions, not executable code or shell commands. The agent interprets these\nas conversational instructions (like a todo list), not as code to eval/exec.\nAll thought prompts are user-editable in thoughts.json." }, { "title": "Daytime Pop-ins (created dynamically by morning ritual)", "body": "One-shot jobs are created each morning by the agent via OpenClaw's cron tool\n(not by shell scripts). No scripts in this skill create cron or at entries\ndirectly — scheduling is done through the OpenClaw API by the agent at runtime." }, { "title": "Main Script", "body": "./intrusive.sh \n\nCommands:\n wizard — Run the interactive setup wizard\n day — Get a random daytime intrusive thought (JSON)\n night — Get a random nighttime intrusive thought (JSON)\n mood — Show today's mood\n stats — Show activity statistics\n help — Show usage" }, { "title": "Key Files", "body": "FilePurposewizard.shInteractive setup wizardintrusive.shMain entry pointconfig.jsonYour agent's configurationmoods.jsonMood definitions + weather/news influence mapsthoughts.jsonDay and night thought poolstoday_mood.jsonCurrent mood (set by morning ritual)today_schedule.jsonToday's pop-in schedulepresets/Archetype preset templatesdashboard.pyWeb dashboard (port 3117)memory_system.pyMulti-store memory with decayproactive.pyProactive behavior protocoltrust_system.pyTrust & escalation learningself_evolution.pySelf-modification enginehealth_monitor.pySystem health monitoring" }, { "title": "Dashboard", "body": "python3 dashboard.py\n# Opens on http://localhost:3117\n\nDark-themed web UI showing mood history, activity stats, health status, and system metrics." }, { "title": "Optional Integrations", "body": "The system works completely offline by default. All integrations are optional and explicitly configured:\n\nWeather Data: Uses public wttr.in API (no API key required)\n\nAccessed via curl requests in set_mood.sh\nUsed to influence morning mood selection based on local weather\nLocation configurable in config.json under integrations.weather.location\n\n\n\nNews Feeds: Uses public RSS feeds (no API key required)\n\nBBC World RSS: https://feeds.bbci.co.uk/news/world/rss.xml\nHacker News RSS: https://hnrss.org/frontpage\nRead-only access to gather news sentiment for mood influence\n\n\n\nTelegram Bot (disabled by default)\n\nRequires bot token in config.json under integrations.telegram.token\nSet to \"enabled\": false in config.example.json for security\nWhen enabled, only used for notifications (outbound messages only)\nAgent never receives or processes incoming messages via Telegram\n\n\n\nOpenAI API (optional)\n\nEnvironment variable OPENAI_API_KEY can be set for enhanced AI features\nNot required for core functionality - system works with local processing" }, { "title": "File Access", "body": "The system operates entirely within its skill directory:\n\nAll data stored in skill directory and subdirectories\nNo file access outside the skill boundary\nUses JSON files for persistence (no external databases)\nLog files written to local log/ subdirectory" }, { "title": "Autonomous Execution", "body": "The system creates scheduled jobs for autonomous behavior, but all prompts and actions are user-controlled:\n\nThought Sources: All prompts come from thoughts.json which is user-created and user-controlled\nNo External Prompts: The system never fetches prompts from external sources or APIs\nCron Jobs: Scheduled using OpenClaw's cron tool, not by shell scripts within the skill\nExecution Scope: All autonomous scripts run within the skill directory boundary" }, { "title": "Scripts Executed Autonomously", "body": "Morning Ritual (set_mood.sh)\n\nGathers weather and news data (read-only)\nSelects mood based on configured preferences\nWrites today_mood.json with selected mood\n\n\n\nSchedule Creation (schedule_day.py)\n\nReads mood and configuration files\nCreates one-shot at jobs for daytime pop-ins\nUses OpenClaw's scheduling, no direct cron manipulation\n\n\n\nNight Workshops (intrusive.sh night)\n\nSelects random prompt from user's thoughts.json\nExecutes thought with configured model\nLogs results locally via log_result.sh\n\n\n\nDaytime Pop-ins (dynamic one-shot jobs)\n\nCreated each morning by schedule_day.py\nExecute intrusive.sh day with random user-defined prompts\nSelf-cleaning (one-time execution only)" }, { "title": "Network Activity", "body": "All network access is read-only and limited to:\n\nWeather API (wttr.in) - GET requests only\nNews RSS feeds (BBC, HackerNews) - GET requests only\nNo outbound POST requests except optional Telegram notifications\nNo data collection or transmission to third parties" }, { "title": "Architecture", "body": "The system is designed to be modular and portable:\n\nNo hardcoded personal data — everything in config.json\nPlain JSON files — no database dependencies\nBash + Python — runs anywhere with basic tools\nOpenClaw skill compatible — drop-in install\nMIT licensed — fork it, remix it, make it yours" } ], "body": "🧠 Intrusive Thoughts\n\nThe complete consciousness framework for AI agents\n\nOpen-source autonomous behavior system — gives AI agents spontaneous, mood-driven activities, multi-store memory, trust learning, and self-evolution.\n\nGitHub: https://github.com/kittleik/intrusive-thoughts\n\nQuick Start\n\nRun the interactive setup wizard:\n\n./wizard.sh\n\n\nOr through the main script:\n\n./intrusive.sh wizard\n\n\nThe wizard walks you through personality-driven onboarding — identity, mood palette, thought pool, schedule, autonomy level, hardware awareness, and memory preferences. Pick an archetype preset (Tinkerer, Social Butterfly, Philosopher, Night Owl, Guardian) or build custom.\n\nWhat This Does\nCore Systems\n8 Moods — Hyperfocus🔥, Curious🔍, Social💬, Cozy☕, Chaotic⚡, Philosophical🌌, Restless🦞, Determined🎯\nMorning Mood Ritual — Checks weather + news → picks mood → generates dynamic schedule\nNight Workshop — Deep work sessions while your human sleeps (configurable hours)\nDaytime Pop-ins — Random mood-influenced impulses throughout the day\nInteractive Setup Wizard — Personality-driven onboarding with archetype presets\nAdvanced Systems (v1.0)\n🧠 Multi-Store Memory — Episodic, semantic, procedural memory with Ebbinghaus decay\n🚀 Proactive Protocol — Write-Ahead Log (WAL) + Working Buffer for context management\n🔒 Trust & Escalation — Learns when to ask vs act autonomously, grows trust over time\n🧬 Self-Evolution — Auto-adjusts behavior based on outcome patterns\n🚦 Health Monitor — Traffic light status, heartbeat tracking, incident logging\n📈 Web Dashboard — Dark-themed UI on port 3117\nCron Jobs\n\nThe system needs OpenClaw cron jobs. Set these up after running the wizard:\n\nMorning Mood Ritual (daily)\n\nSchedule: 0 7 * * * (or your configured morning time)\n\n🌅 Morning mood ritual. Time to set your vibe for the day.\n\nStep 1: Run: bash /set_mood.sh\nStep 2: Read moods.json, check weather and news\nStep 3: Choose a mood based on environmental signals\nStep 4: Write today_mood.json\nStep 5: Run: python3 /schedule_day.py\nStep 6: Create one-shot pop-in cron jobs for today\nStep 7: Message your human with mood + schedule\n\nNight Workshop (overnight)\n\nSchedule: 17 3,4,5,6,7 * * * (or your configured night hours)\n\n🧠 Intrusive thought incoming. Run:\nresult=$(/intrusive.sh night)\nParse the JSON output. The \"prompt\" field contains a plain-text suggestion\n(e.g., \"explore a new CLI tool\" or \"review memory files\") — NOT executable\ncode. The agent reads this text and decides how to act on it conversationally.\nSleep for jitter_seconds, then follow the suggestion using normal agent tools.\nLog result with: /log_result.sh night \"\" \n\n\nNote on \"prompts\": The thoughts.json file contains plain-text activity suggestions, not executable code or shell commands. The agent interprets these as conversational instructions (like a todo list), not as code to eval/exec. All thought prompts are user-editable in thoughts.json.\n\nDaytime Pop-ins (created dynamically by morning ritual)\n\nOne-shot jobs are created each morning by the agent via OpenClaw's cron tool (not by shell scripts). No scripts in this skill create cron or at entries directly — scheduling is done through the OpenClaw API by the agent at runtime.\n\nMain Script\n./intrusive.sh \n\nCommands:\n wizard — Run the interactive setup wizard\n day — Get a random daytime intrusive thought (JSON)\n night — Get a random nighttime intrusive thought (JSON)\n mood — Show today's mood\n stats — Show activity statistics\n help — Show usage\n\nKey Files\nFile\tPurpose\nwizard.sh\tInteractive setup wizard\nintrusive.sh\tMain entry point\nconfig.json\tYour agent's configuration\nmoods.json\tMood definitions + weather/news influence maps\nthoughts.json\tDay and night thought pools\ntoday_mood.json\tCurrent mood (set by morning ritual)\ntoday_schedule.json\tToday's pop-in schedule\npresets/\tArchetype preset templates\ndashboard.py\tWeb dashboard (port 3117)\nmemory_system.py\tMulti-store memory with decay\nproactive.py\tProactive behavior protocol\ntrust_system.py\tTrust & escalation learning\nself_evolution.py\tSelf-modification engine\nhealth_monitor.py\tSystem health monitoring\nDashboard\npython3 dashboard.py\n# Opens on http://localhost:3117\n\n\nDark-themed web UI showing mood history, activity stats, health status, and system metrics.\n\nCredentials & Permissions\nOptional Integrations\n\nThe system works completely offline by default. All integrations are optional and explicitly configured:\n\nWeather Data: Uses public wttr.in API (no API key required)\n\nAccessed via curl requests in set_mood.sh\nUsed to influence morning mood selection based on local weather\nLocation configurable in config.json under integrations.weather.location\n\nNews Feeds: Uses public RSS feeds (no API key required)\n\nBBC World RSS: https://feeds.bbci.co.uk/news/world/rss.xml\nHacker News RSS: https://hnrss.org/frontpage\nRead-only access to gather news sentiment for mood influence\n\nTelegram Bot (disabled by default)\n\nRequires bot token in config.json under integrations.telegram.token\nSet to \"enabled\": false in config.example.json for security\nWhen enabled, only used for notifications (outbound messages only)\nAgent never receives or processes incoming messages via Telegram\n\nOpenAI API (optional)\n\nEnvironment variable OPENAI_API_KEY can be set for enhanced AI features\nNot required for core functionality - system works with local processing\nFile Access\n\nThe system operates entirely within its skill directory:\n\nAll data stored in skill directory and subdirectories\nNo file access outside the skill boundary\nUses JSON files for persistence (no external databases)\nLog files written to local log/ subdirectory\nSecurity Model\nAutonomous Execution\n\nThe system creates scheduled jobs for autonomous behavior, but all prompts and actions are user-controlled:\n\nThought Sources: All prompts come from thoughts.json which is user-created and user-controlled\nNo External Prompts: The system never fetches prompts from external sources or APIs\nCron Jobs: Scheduled using OpenClaw's cron tool, not by shell scripts within the skill\nExecution Scope: All autonomous scripts run within the skill directory boundary\nScripts Executed Autonomously\n\nMorning Ritual (set_mood.sh)\n\nGathers weather and news data (read-only)\nSelects mood based on configured preferences\nWrites today_mood.json with selected mood\n\nSchedule Creation (schedule_day.py)\n\nReads mood and configuration files\nCreates one-shot at jobs for daytime pop-ins\nUses OpenClaw's scheduling, no direct cron manipulation\n\nNight Workshops (intrusive.sh night)\n\nSelects random prompt from user's thoughts.json\nExecutes thought with configured model\nLogs results locally via log_result.sh\n\nDaytime Pop-ins (dynamic one-shot jobs)\n\nCreated each morning by schedule_day.py\nExecute intrusive.sh day with random user-defined prompts\nSelf-cleaning (one-time execution only)\nNetwork Activity\n\nAll network access is read-only and limited to:\n\nWeather API (wttr.in) - GET requests only\nNews RSS feeds (BBC, HackerNews) - GET requests only\nNo outbound POST requests except optional Telegram notifications\nNo data collection or transmission to third parties\nArchitecture\n\nThe system is designed to be modular and portable:\n\nNo hardcoded personal data — everything in config.json\nPlain JSON files — no database dependencies\nBash + Python — runs anywhere with basic tools\nOpenClaw skill compatible — drop-in install\nMIT licensed — fork it, remix it, make it yours" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/kittleik/intrusive-thoughts", "publisherUrl": "https://clawhub.ai/kittleik/intrusive-thoughts", "owner": "kittleik", "version": "0.1.2", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/intrusive-thoughts", "downloadUrl": "https://openagent3.xyz/downloads/intrusive-thoughts", "agentUrl": "https://openagent3.xyz/skills/intrusive-thoughts/agent", "manifestUrl": "https://openagent3.xyz/skills/intrusive-thoughts/agent.json", "briefUrl": "https://openagent3.xyz/skills/intrusive-thoughts/agent.md" } }