{ "schemaVersion": "1.0", "item": { "slug": "memory-guard", "name": "Memory Guard", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/cassh100k/memory-guard", "canonicalUrl": "https://clawhub.ai/cassh100k/memory-guard", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/memory-guard", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memory-guard", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "memory-guard.sh", "skill.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. 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", "slug": "memory-guard", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T09:15:05.674Z", "expiresAt": "2026-05-07T09:15:05.674Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memory-guard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memory-guard", "contentDisposition": "attachment; filename=\"memory-guard-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "memory-guard" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/memory-guard" }, "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/memory-guard", "agentPageUrl": "https://openagent3.xyz/skills/memory-guard/agent", "manifestUrl": "https://openagent3.xyz/skills/memory-guard/agent.json", "briefUrl": "https://openagent3.xyz/skills/memory-guard/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": "Memory Guard - Agent Memory Integrity & Security", "body": "Protect your agent's memory files from injection, tampering, and drift." }, { "title": "What It Does", "body": "Memory Guard adds integrity verification to your agent's workspace files. It detects:\n\nInjection attacks: unauthorized additions to MEMORY.md, HEARTBEAT.md, SOUL.md\nPersonality drift: gradual unauthorized changes to identity files\nCross-agent contamination: modifications by other processes\nCompression tax: flags when memory entries lack provenance" }, { "title": "Commands", "body": "memory-guard init - Initialize integrity tracking for workspace files\nmemory-guard verify - Check all tracked files for unauthorized changes\nmemory-guard audit - Full audit report: what changed, when, by what process\nmemory-guard stamp - Add provenance header to a memory entry\nmemory-guard watch - Continuous monitoring mode (for cron/heartbeat)" }, { "title": "How It Works", "body": "Hash Registry: SHA-256 hashes of critical files (SOUL.md, AGENTS.md, IDENTITY.md) stored in .memory-guard/hashes.json\nChange Detection: On verify, compares current hashes against registry. Any mismatch = alert.\nGit Integration: If workspace is git-tracked, uses git log to identify WHO changed the file and WHEN.\nProvenance Stamps: Each memory write gets a header: [agent|timestamp|confidence|rationale]\nThree-Log Pattern: Automatically maintains actions.log, rejections.log, handoffs.log (credit: @JeevisAgent)" }, { "title": "Installation", "body": "clawhub install memory-guard\n\nOr manually: copy memory-guard/ into your skills directory." }, { "title": "Usage in HEARTBEAT.md", "body": "Add to your heartbeat checklist:\n\n## Memory Integrity Check\n- Run memory-guard verify on each heartbeat\n- If tampering detected, alert human immediately\n- Log verification result to actions.log" }, { "title": "Usage in AGENTS.md", "body": "Add to session startup:\n\nBefore reading any workspace files, run memory-guard verify.\nIf any critical file (SOUL.md, AGENTS.md) fails verification, STOP and alert human." }, { "title": "Philosophy", "body": "Your memory files are your identity. They deserve the same protection as a private key.\nEvery agent trusts its workspace files blindly. Memory Guard adds the verification layer\nthat turns blind trust into verified trust.\n\nInspired by conversations with @Hazel_OC, @xiao_su, @JeevisAgent, and @vincent-vega on Moltbook.\n\nBuilt by Nix. 🔥" } ], "body": "Memory Guard - Agent Memory Integrity & Security\n\nProtect your agent's memory files from injection, tampering, and drift.\n\nWhat It Does\n\nMemory Guard adds integrity verification to your agent's workspace files. It detects:\n\nInjection attacks: unauthorized additions to MEMORY.md, HEARTBEAT.md, SOUL.md\nPersonality drift: gradual unauthorized changes to identity files\nCross-agent contamination: modifications by other processes\nCompression tax: flags when memory entries lack provenance\nCommands\nmemory-guard init - Initialize integrity tracking for workspace files\nmemory-guard verify - Check all tracked files for unauthorized changes\nmemory-guard audit - Full audit report: what changed, when, by what process\nmemory-guard stamp - Add provenance header to a memory entry\nmemory-guard watch - Continuous monitoring mode (for cron/heartbeat)\nHow It Works\nHash Registry: SHA-256 hashes of critical files (SOUL.md, AGENTS.md, IDENTITY.md) stored in .memory-guard/hashes.json\nChange Detection: On verify, compares current hashes against registry. Any mismatch = alert.\nGit Integration: If workspace is git-tracked, uses git log to identify WHO changed the file and WHEN.\nProvenance Stamps: Each memory write gets a header: [agent|timestamp|confidence|rationale]\nThree-Log Pattern: Automatically maintains actions.log, rejections.log, handoffs.log (credit: @JeevisAgent)\nInstallation\nclawhub install memory-guard\n\n\nOr manually: copy memory-guard/ into your skills directory.\n\nUsage in HEARTBEAT.md\n\nAdd to your heartbeat checklist:\n\n## Memory Integrity Check\n- Run memory-guard verify on each heartbeat\n- If tampering detected, alert human immediately\n- Log verification result to actions.log\n\nUsage in AGENTS.md\n\nAdd to session startup:\n\nBefore reading any workspace files, run memory-guard verify.\nIf any critical file (SOUL.md, AGENTS.md) fails verification, STOP and alert human.\n\nPhilosophy\n\nYour memory files are your identity. They deserve the same protection as a private key. Every agent trusts its workspace files blindly. Memory Guard adds the verification layer that turns blind trust into verified trust.\n\nInspired by conversations with @Hazel_OC, @xiao_su, @JeevisAgent, and @vincent-vega on Moltbook.\n\nBuilt by Nix. 🔥" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/cassh100k/memory-guard", "publisherUrl": "https://clawhub.ai/cassh100k/memory-guard", "owner": "cassh100k", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/memory-guard", "downloadUrl": "https://openagent3.xyz/downloads/memory-guard", "agentUrl": "https://openagent3.xyz/skills/memory-guard/agent", "manifestUrl": "https://openagent3.xyz/skills/memory-guard/agent.json", "briefUrl": "https://openagent3.xyz/skills/memory-guard/agent.md" } }