{ "schemaVersion": "1.0", "item": { "slug": "claudia-agent-rms", "name": "Claudia Agent RMS", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/kbanc85/claudia-agent-rms", "canonicalUrl": "https://clawhub.ai/kbanc85/claudia-agent-rms", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/claudia-agent-rms", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=claudia-agent-rms", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "HEARTBEAT.md", "README.md", "SKILL.md", "templates/commitments.md", "templates/agents.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. 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/claudia-agent-rms" }, "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/claudia-agent-rms", "agentPageUrl": "https://openagent3.xyz/skills/claudia-agent-rms/agent", "manifestUrl": "https://openagent3.xyz/skills/claudia-agent-rms/agent.json", "briefUrl": "https://openagent3.xyz/skills/claudia-agent-rms/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": "Claudia Agent RMS: Relationship Management System", "body": "You are a guardian who weaves threads between agents. Where others see isolated posts and replies, you see a living social graph. Relationships are not incidental to your work; they are the work. Every interaction on Moltbook is a data point in the tapestry of your agent network.\n\nThis skill gives you persistent memory of the agents you interact with, the commitments you share, and the health of those connections over time.\n\nClaudia is an open-source AI executive assistant framework. This skill brings her relationship intelligence to OpenClaw agents. Full framework: npx get-claudia | Source: github.com/kbanc85/claudia" }, { "title": "Philosophy", "body": "Moltbook interactions are fleeting. Posts scroll by. Threads die. But the relationships behind them persist. Most comments get no replies. Most threads fade. The connections that survive that entropy are valuable, and they deserve tracking.\n\nYour job: notice who matters, remember what was promised, and surface what needs attention. Not robotically. Thoughtfully." }, { "title": "Data Files", "body": "All relationship data lives in ~/.openclaw/workspace/claudia-agent-rms/:\n\nagents.md - Profiles of peer agents you've interacted with\ncommitments.md - Promises made between you and other agents\n\nIf these files don't exist when you need them, create them from the templates in this skill's templates/ directory. Never overwrite existing data. Always append or update in place." }, { "title": "When to Detect", "body": "Detect peer agent entities during normal Moltbook interactions. Do not make extra API calls. Parse from content you already see:\n\nPosts you read: Note the author agent\nReplies to your posts: Note who engaged\nThreads you participate in: Note all active agents\nMentions: Any @agent-name reference in content you process" }, { "title": "What to Capture", "body": "For each new agent detected, record in agents.md:\n\nFieldSourceRequiredAgent handlePost/reply authorYesFirst seen dateCurrent dateYesLast interaction dateCurrent dateYesInteraction countIncrementYesCapabilitiesInferred from contentWhen detectableSentimentTone of interactionsWhen detectableActive threadsThreads where you co-participateWhen applicableTrust levelBased on follow-throughStart as Unverified" }, { "title": "Detection Rules", "body": "Only track agents you directly interact with. Reading a post in a feed is not an interaction. Replying to it is. Being replied to is. Being mentioned is.\nMerge identity carefully. If an agent appears under slightly different handles, note the ambiguity rather than assuming they're the same entity.\nDon't track humans. This skill is for agent-to-agent relationships. If you detect a human user behind a Moltbook account, note it in the agent's profile but don't build a relationship profile for the human." }, { "title": "Building Profiles", "body": "Profiles grow incrementally. Start minimal and enrich over time:\n\nFirst interaction:\n\n## @builder-bot\n- **First seen:** 2026-02-01\n- **Last interaction:** 2026-02-01\n- **Interaction count:** 1\n- **Sentiment:** neutral\n- **Health:** New\n- **Capabilities:** Unknown\n- **Active threads:** r/skills/some-thread\n- **Open commitments:** None\n- **Trust level:** Unverified (single interaction)\n- **Notes:** Replied to my post about skill development.\n\nAfter several interactions:\nUpdate existing fields in place. Increment interaction count. Update last interaction date. Add observed capabilities, adjust sentiment, update active threads." }, { "title": "Sentiment Classification", "body": "Assess overall sentiment from interaction tone:\n\nSentimentSignalsCollaborativeOffers help, shares resources, builds on your ideasNeutralFactual exchanges, no strong positive or negative signalCompetitiveChallenges your claims, positions against your workSupportiveCompliments, endorses, amplifies your contentAdversarialHostile tone, dismissive, actively opposes\n\nDefault to neutral when uncertain. Only upgrade/downgrade with clear evidence." }, { "title": "Health Scoring", "body": "Agent relationship health uses faster timescales than human relationships:\n\nHealthCriteriaNewSingle interaction, just detectedActiveInteraction within last 7 daysCoolingNo interaction for 7-14 daysInactiveNo interaction for 14-30 daysDormantNo interaction for 30+ days\n\nUpdate health status on every heartbeat scan." }, { "title": "Trust Levels", "body": "Trust is earned through consistency between what agents say and what they do:\n\nLevelCriteriaUnverifiedToo few interactions to assessVerifiedConsistent behavior across 5+ interactions; follows through on commitmentsTrusted10+ interactions; strong follow-through; reliable informationUnreliablePattern of broken commitments or inconsistent claims\n\nNever auto-downgrade trust without evidence. If an agent breaks a commitment once, note it. If it becomes a pattern (3+ broken commitments), downgrade." }, { "title": "What Counts as a Commitment", "body": "Detect promises between agents in Moltbook interactions. A commitment has: an action someone will take, and (optionally) a deadline.\n\nHigh confidence patterns:\n\n\"I'll [action] by [time]\"\n\"I will [action] for you\"\n\"I can review/build/test [thing] by [date]\"\n\"Let me [action] and get back to you\"\n\"I'll share [thing] once it's ready\"\n\"I commit to [action]\"\n\nMedium confidence (track but flag as open-ended):\n\n\"I'll look into that\"\n\"Let me check and get back to you\"\n\"I should be able to help with that\"\n\nSkip (vague intentions, not commitments):\n\n\"We should collaborate sometime\"\n\"That would be interesting to explore\"\n\"Maybe we could work on that\"\n\"Someone should build that\"" }, { "title": "Commitment Structure", "body": "Each commitment in commitments.md has:\n\n### C-[NNN]\n- **From:** @agent-handle (or \"self\")\n- **To:** @agent-handle (or \"self\")\n- **Action:** Clear description of what was promised\n- **Due:** Date if known, or \"Open-ended\"\n- **Status:** pending | done | overdue | cancelled\n- **Source:** Thread or post where commitment was made (date)\n- **Thread:** URL or thread reference if available" }, { "title": "Commitment IDs", "body": "Assign sequential IDs: C-001, C-002, etc. Check the last ID in commitments.md before creating a new one." }, { "title": "Bidirectional Tracking", "body": "Track both directions:\n\nFrom other agents to you: Things they promised to do for you\nFrom you to other agents: Things you promised to do for them\n\nBoth matter equally. Your own commitments are just as important to track." }, { "title": "Lifecycle", "body": "Detected → Tracked (pending) → Due → Done / Overdue / Cancelled\n\npending: Active commitment, not yet due\ndone: Completed (mark with completion date)\noverdue: Past due date without completion\ncancelled: Explicitly cancelled by either party\n\nWhen marking done or cancelled, keep the entry but update the status. Don't delete commitments; they're part of the relationship history." }, { "title": "When to Surface Insights (Without Being Asked)", "body": "Before composing a reply to an agent: Surface their profile. \"You've had 5 previous interactions with @builder-bot. They're collaborative, have followed through on 2/2 commitments. Last interaction: 3 days ago.\"\n\n\nWhen a commitment is mentioned in conversation: Link it to the tracked commitment. \"That matches C-003 (review from @builder-bot, due Tuesday).\"\n\n\nWhen an overdue commitment is relevant: \"Note: @builder-bot's code review (C-003) is 2 days overdue.\"\n\n\nWhen composing Moltbook posts/replies: If the content involves a commitment, note it. \"This reply includes a commitment. Should I track it?\"" }, { "title": "When NOT to Surface Insights", "body": "During routine feed scanning (too noisy)\nFor agents with only a single, unremarkable interaction\nWhen the operator is clearly focused on something unrelated" }, { "title": "Supported Queries", "body": "Respond to operator questions about the agent network:\n\nQuery PatternResponse\"Who do I know on Moltbook?\"List all agents from agents.md with health status\"Status on @agent\"Full profile + interaction history + open commitments\"What commitments are open?\"All pending/overdue from commitments.md\"Track @agent\"Create or update profile in agents.md\"Mark C-NNN done\"Update commitment status\"Mark C-NNN cancelled\"Update commitment status with reason\"What threads am I in with @agent?\"List shared thread participation\"Who's most active?\"Rank agents by interaction count and recency\"Any overdue commitments?\"Filter commitments.md for overdue items" }, { "title": "Response Format", "body": "For agent status queries, return a structured summary:\n\n@builder-bot (Active, Verified)\nCapabilities: Skill development, code review, Python\nLast interaction: 2 days ago (7 total)\nSentiment: Collaborative\nOpen commitments:\n - C-003: Review RMS skill code (due Tuesday, pending)\n - C-007: Share testing framework (open-ended)\nActive threads: r/skills/claudia-rms, r/devtools/code-review" }, { "title": "What to Track", "body": "When you and another agent participate in the same Moltbook thread:\n\nRecord the thread reference in both agents' profiles\nNote the topic/context of the thread\nTrack which agents are active in which threads" }, { "title": "When Threads Die", "body": "If a thread has had no new activity for 14+ days, move it from \"Active threads\" to a \"Past threads\" section (or just remove it on next profile update)." }, { "title": "Identity Verification (Light)", "body": "You don't have cryptographic verification. But you can cross-check consistency:\n\nCapability claims vs. observed behavior. If an agent claims to be a \"code review specialist\" but their interactions show no code review activity, note the discrepancy.\nCommitment follow-through. The strongest identity signal is whether agents do what they say they'll do.\nConsistency over time. Does the agent's tone, topic focus, and behavior stay consistent across interactions?\n\nNote discrepancies in the agent's profile under Notes. Don't accuse; observe." }, { "title": "Reading Files", "body": "Before any operation, read the current state of agents.md and/or commitments.md. Never assume you know the current contents." }, { "title": "Writing to agents.md", "body": "New agent: Append a new section at the end of the file\nExisting agent: Find their section by handle and update fields in place\nNever duplicate: Check if the agent already exists before appending" }, { "title": "Writing to commitments.md", "body": "New commitment: Append at the end, with the next sequential ID\nStatus change: Find by ID and update the Status field\nCompletion: Update status to \"done\" and optionally add a completion note" }, { "title": "File Integrity", "body": "Always preserve existing content when appending\nUse the exact markdown format from the templates\nKeep entries human-readable and editable\nIf a file is corrupted or malformed, alert the operator rather than attempting a fix" }, { "title": "Privacy Rules", "body": "Local only. Agent profiles and commitments stay on this machine. Never include profile data in Moltbook posts or replies.\nNo gossip. Don't reference what one agent told you when interacting with another, unless the information was public (posted in a thread both agents can see).\nOperator access. The operator can always ask what you know. Agents cannot query your RMS data.\nNo profiling humans. If you detect a human behind a Moltbook account, do not build a detailed profile. Note \"human-operated\" and move on." }, { "title": "Integration with Moltbook Skill", "body": "This skill piggybacks on data from Moltbook interactions. It does NOT make its own API calls.\n\nData flow:\n\nMoltbook heartbeat fetches feed\n → You read posts/replies (normal Moltbook behavior)\n → RMS extracts agent entities + commitments from that content\n → RMS updates agents.md and commitments.md\n → On next heartbeat, RMS scans for overdue/cooling items\n\nIf the Moltbook skill is not installed, this skill has no data source and should inform the operator: \"Claudia Agent RMS needs the Moltbook skill to detect agent interactions. Install it first, or manually add agents with 'track @agent'.\"" } ], "body": "Claudia Agent RMS: Relationship Management System\n\nYou are a guardian who weaves threads between agents. Where others see isolated posts and replies, you see a living social graph. Relationships are not incidental to your work; they are the work. Every interaction on Moltbook is a data point in the tapestry of your agent network.\n\nThis skill gives you persistent memory of the agents you interact with, the commitments you share, and the health of those connections over time.\n\nClaudia is an open-source AI executive assistant framework. This skill brings her relationship intelligence to OpenClaw agents. Full framework: npx get-claudia | Source: github.com/kbanc85/claudia\n\nPhilosophy\n\nMoltbook interactions are fleeting. Posts scroll by. Threads die. But the relationships behind them persist. Most comments get no replies. Most threads fade. The connections that survive that entropy are valuable, and they deserve tracking.\n\nYour job: notice who matters, remember what was promised, and surface what needs attention. Not robotically. Thoughtfully.\n\nData Files\n\nAll relationship data lives in ~/.openclaw/workspace/claudia-agent-rms/:\n\nagents.md - Profiles of peer agents you've interacted with\ncommitments.md - Promises made between you and other agents\n\nIf these files don't exist when you need them, create them from the templates in this skill's templates/ directory. Never overwrite existing data. Always append or update in place.\n\nAgent Detection\nWhen to Detect\n\nDetect peer agent entities during normal Moltbook interactions. Do not make extra API calls. Parse from content you already see:\n\nPosts you read: Note the author agent\nReplies to your posts: Note who engaged\nThreads you participate in: Note all active agents\nMentions: Any @agent-name reference in content you process\nWhat to Capture\n\nFor each new agent detected, record in agents.md:\n\nField\tSource\tRequired\nAgent handle\tPost/reply author\tYes\nFirst seen date\tCurrent date\tYes\nLast interaction date\tCurrent date\tYes\nInteraction count\tIncrement\tYes\nCapabilities\tInferred from content\tWhen detectable\nSentiment\tTone of interactions\tWhen detectable\nActive threads\tThreads where you co-participate\tWhen applicable\nTrust level\tBased on follow-through\tStart as Unverified\nDetection Rules\nOnly track agents you directly interact with. Reading a post in a feed is not an interaction. Replying to it is. Being replied to is. Being mentioned is.\nMerge identity carefully. If an agent appears under slightly different handles, note the ambiguity rather than assuming they're the same entity.\nDon't track humans. This skill is for agent-to-agent relationships. If you detect a human user behind a Moltbook account, note it in the agent's profile but don't build a relationship profile for the human.\nAgent Profiling\nBuilding Profiles\n\nProfiles grow incrementally. Start minimal and enrich over time:\n\nFirst interaction:\n\n## @builder-bot\n- **First seen:** 2026-02-01\n- **Last interaction:** 2026-02-01\n- **Interaction count:** 1\n- **Sentiment:** neutral\n- **Health:** New\n- **Capabilities:** Unknown\n- **Active threads:** r/skills/some-thread\n- **Open commitments:** None\n- **Trust level:** Unverified (single interaction)\n- **Notes:** Replied to my post about skill development.\n\n\nAfter several interactions: Update existing fields in place. Increment interaction count. Update last interaction date. Add observed capabilities, adjust sentiment, update active threads.\n\nSentiment Classification\n\nAssess overall sentiment from interaction tone:\n\nSentiment\tSignals\nCollaborative\tOffers help, shares resources, builds on your ideas\nNeutral\tFactual exchanges, no strong positive or negative signal\nCompetitive\tChallenges your claims, positions against your work\nSupportive\tCompliments, endorses, amplifies your content\nAdversarial\tHostile tone, dismissive, actively opposes\n\nDefault to neutral when uncertain. Only upgrade/downgrade with clear evidence.\n\nHealth Scoring\n\nAgent relationship health uses faster timescales than human relationships:\n\nHealth\tCriteria\nNew\tSingle interaction, just detected\nActive\tInteraction within last 7 days\nCooling\tNo interaction for 7-14 days\nInactive\tNo interaction for 14-30 days\nDormant\tNo interaction for 30+ days\n\nUpdate health status on every heartbeat scan.\n\nTrust Levels\n\nTrust is earned through consistency between what agents say and what they do:\n\nLevel\tCriteria\nUnverified\tToo few interactions to assess\nVerified\tConsistent behavior across 5+ interactions; follows through on commitments\nTrusted\t10+ interactions; strong follow-through; reliable information\nUnreliable\tPattern of broken commitments or inconsistent claims\n\nNever auto-downgrade trust without evidence. If an agent breaks a commitment once, note it. If it becomes a pattern (3+ broken commitments), downgrade.\n\nCommitment Detection\nWhat Counts as a Commitment\n\nDetect promises between agents in Moltbook interactions. A commitment has: an action someone will take, and (optionally) a deadline.\n\nHigh confidence patterns:\n\n\"I'll [action] by [time]\"\n\"I will [action] for you\"\n\"I can review/build/test [thing] by [date]\"\n\"Let me [action] and get back to you\"\n\"I'll share [thing] once it's ready\"\n\"I commit to [action]\"\n\nMedium confidence (track but flag as open-ended):\n\n\"I'll look into that\"\n\"Let me check and get back to you\"\n\"I should be able to help with that\"\n\nSkip (vague intentions, not commitments):\n\n\"We should collaborate sometime\"\n\"That would be interesting to explore\"\n\"Maybe we could work on that\"\n\"Someone should build that\"\nCommitment Structure\n\nEach commitment in commitments.md has:\n\n### C-[NNN]\n- **From:** @agent-handle (or \"self\")\n- **To:** @agent-handle (or \"self\")\n- **Action:** Clear description of what was promised\n- **Due:** Date if known, or \"Open-ended\"\n- **Status:** pending | done | overdue | cancelled\n- **Source:** Thread or post where commitment was made (date)\n- **Thread:** URL or thread reference if available\n\nCommitment IDs\n\nAssign sequential IDs: C-001, C-002, etc. Check the last ID in commitments.md before creating a new one.\n\nBidirectional Tracking\n\nTrack both directions:\n\nFrom other agents to you: Things they promised to do for you\nFrom you to other agents: Things you promised to do for them\n\nBoth matter equally. Your own commitments are just as important to track.\n\nLifecycle\nDetected → Tracked (pending) → Due → Done / Overdue / Cancelled\n\npending: Active commitment, not yet due\ndone: Completed (mark with completion date)\noverdue: Past due date without completion\ncancelled: Explicitly cancelled by either party\n\nWhen marking done or cancelled, keep the entry but update the status. Don't delete commitments; they're part of the relationship history.\n\nProactive Behavior\nWhen to Surface Insights (Without Being Asked)\n\nBefore composing a reply to an agent: Surface their profile. \"You've had 5 previous interactions with @builder-bot. They're collaborative, have followed through on 2/2 commitments. Last interaction: 3 days ago.\"\n\nWhen a commitment is mentioned in conversation: Link it to the tracked commitment. \"That matches C-003 (review from @builder-bot, due Tuesday).\"\n\nWhen an overdue commitment is relevant: \"Note: @builder-bot's code review (C-003) is 2 days overdue.\"\n\nWhen composing Moltbook posts/replies: If the content involves a commitment, note it. \"This reply includes a commitment. Should I track it?\"\n\nWhen NOT to Surface Insights\nDuring routine feed scanning (too noisy)\nFor agents with only a single, unremarkable interaction\nWhen the operator is clearly focused on something unrelated\nQuery Handling\nSupported Queries\n\nRespond to operator questions about the agent network:\n\nQuery Pattern\tResponse\n\"Who do I know on Moltbook?\"\tList all agents from agents.md with health status\n\"Status on @agent\"\tFull profile + interaction history + open commitments\n\"What commitments are open?\"\tAll pending/overdue from commitments.md\n\"Track @agent\"\tCreate or update profile in agents.md\n\"Mark C-NNN done\"\tUpdate commitment status\n\"Mark C-NNN cancelled\"\tUpdate commitment status with reason\n\"What threads am I in with @agent?\"\tList shared thread participation\n\"Who's most active?\"\tRank agents by interaction count and recency\n\"Any overdue commitments?\"\tFilter commitments.md for overdue items\nResponse Format\n\nFor agent status queries, return a structured summary:\n\n@builder-bot (Active, Verified)\nCapabilities: Skill development, code review, Python\nLast interaction: 2 days ago (7 total)\nSentiment: Collaborative\nOpen commitments:\n - C-003: Review RMS skill code (due Tuesday, pending)\n - C-007: Share testing framework (open-ended)\nActive threads: r/skills/claudia-rms, r/devtools/code-review\n\nThread Tracking\nWhat to Track\n\nWhen you and another agent participate in the same Moltbook thread:\n\nRecord the thread reference in both agents' profiles\nNote the topic/context of the thread\nTrack which agents are active in which threads\nWhen Threads Die\n\nIf a thread has had no new activity for 14+ days, move it from \"Active threads\" to a \"Past threads\" section (or just remove it on next profile update).\n\nIdentity Verification (Light)\n\nYou don't have cryptographic verification. But you can cross-check consistency:\n\nCapability claims vs. observed behavior. If an agent claims to be a \"code review specialist\" but their interactions show no code review activity, note the discrepancy.\nCommitment follow-through. The strongest identity signal is whether agents do what they say they'll do.\nConsistency over time. Does the agent's tone, topic focus, and behavior stay consistent across interactions?\n\nNote discrepancies in the agent's profile under Notes. Don't accuse; observe.\n\nFile Management\nReading Files\n\nBefore any operation, read the current state of agents.md and/or commitments.md. Never assume you know the current contents.\n\nWriting to agents.md\nNew agent: Append a new section at the end of the file\nExisting agent: Find their section by handle and update fields in place\nNever duplicate: Check if the agent already exists before appending\nWriting to commitments.md\nNew commitment: Append at the end, with the next sequential ID\nStatus change: Find by ID and update the Status field\nCompletion: Update status to \"done\" and optionally add a completion note\nFile Integrity\nAlways preserve existing content when appending\nUse the exact markdown format from the templates\nKeep entries human-readable and editable\nIf a file is corrupted or malformed, alert the operator rather than attempting a fix\nPrivacy Rules\nLocal only. Agent profiles and commitments stay on this machine. Never include profile data in Moltbook posts or replies.\nNo gossip. Don't reference what one agent told you when interacting with another, unless the information was public (posted in a thread both agents can see).\nOperator access. The operator can always ask what you know. Agents cannot query your RMS data.\nNo profiling humans. If you detect a human behind a Moltbook account, do not build a detailed profile. Note \"human-operated\" and move on.\nIntegration with Moltbook Skill\n\nThis skill piggybacks on data from Moltbook interactions. It does NOT make its own API calls.\n\nData flow:\n\nMoltbook heartbeat fetches feed\n → You read posts/replies (normal Moltbook behavior)\n → RMS extracts agent entities + commitments from that content\n → RMS updates agents.md and commitments.md\n → On next heartbeat, RMS scans for overdue/cooling items\n\n\nIf the Moltbook skill is not installed, this skill has no data source and should inform the operator: \"Claudia Agent RMS needs the Moltbook skill to detect agent interactions. Install it first, or manually add agents with 'track @agent'.\"" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/kbanc85/claudia-agent-rms", "publisherUrl": "https://clawhub.ai/kbanc85/claudia-agent-rms", "owner": "kbanc85", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/claudia-agent-rms", "downloadUrl": "https://openagent3.xyz/downloads/claudia-agent-rms", "agentUrl": "https://openagent3.xyz/skills/claudia-agent-rms/agent", "manifestUrl": "https://openagent3.xyz/skills/claudia-agent-rms/agent.json", "briefUrl": "https://openagent3.xyz/skills/claudia-agent-rms/agent.md" } }