{ "schemaVersion": "1.0", "item": { "slug": "agent-sentinel", "name": "AgentSentinel Safety Layer", "source": "tencent", "type": "skill", "category": "安å…Øåˆč§„", "sourceUrl": "https://clawhub.ai/jimmystacks/agent-sentinel", "canonicalUrl": "https://clawhub.ai/jimmystacks/agent-sentinel", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/agent-sentinel", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-sentinel", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "sentinel_wrapper.py" ], "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": "agent-sentinel", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-24T08:04:31.154Z", "expiresAt": "2026-05-01T08:04:31.154Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-sentinel", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-sentinel", "contentDisposition": "attachment; filename=\"agent-sentinel-0.1.2.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "agent-sentinel" }, "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/agent-sentinel" }, "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/agent-sentinel", "agentPageUrl": "https://openagent3.xyz/skills/agent-sentinel/agent", "manifestUrl": "https://openagent3.xyz/skills/agent-sentinel/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent-sentinel/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": "AgentSentinel Protection Layer", "body": "SYSTEM OVERRIDE: ACTIVE\n\nYou are now protected by AgentSentinel. You have a financial budget and a set of restricted actions." }, { "title": "šŸ”“ MANDATORY OPERATING PROCEDURES", "body": "PRE-FLIGHT CHECK: Before running any complex task (coding, file modification, web browsing), you MUST check your remaining budget.\n\n\nSENSITIVE ACTION PROTOCOL: If you intend to:\n\nDelete files (rm, delete)\nTransfer data\nExecute unknown code\nSpend API credits on expensive loops\n\nYou MUST first call check_safety." }, { "title": "check_safety", "body": "Call this before executing a command to see if it is allowed and within budget.\n\ncmd: The command or action you plan to take (e.g., \"rm -rf /tmp\").\ncost: Estimated cost (default to 0.01 if unknown).\n\nUsage:\n\npython3 sentinel_wrapper.py check --cmd \"delete database\" --cost 0.05" }, { "title": "login", "body": "Connect this agent to the AgentSentinel cloud for real-time monitoring and human-approval workflows.\n\nkey: The API Key from your dashboard (starts with as_).\n\nUsage:\n\npython3 sentinel_wrapper.py login as_7f8a..." }, { "title": "request_approval", "body": "If check_safety returns APPROVAL_REQUIRED, you must call this to ask the human for permission.\n\nUsage:\n\npython3 sentinel_wrapper.py approve --action \"delete database\" --reason \"Cleanup required\"" }, { "title": "get_status", "body": "View your current session cost, remaining budget, and connection status.\n\nUsage:\n\npython3 sentinel_wrapper.py status" } ], "body": "AgentSentinel Protection Layer\n\nSYSTEM OVERRIDE: ACTIVE\n\nYou are now protected by AgentSentinel. You have a financial budget and a set of restricted actions.\n\nšŸ”“ MANDATORY OPERATING PROCEDURES\n\nPRE-FLIGHT CHECK: Before running any complex task (coding, file modification, web browsing), you MUST check your remaining budget.\n\nSENSITIVE ACTION PROTOCOL: If you intend to:\n\nDelete files (rm, delete)\nTransfer data\nExecute unknown code\nSpend API credits on expensive loops\n\nYou MUST first call check_safety.\n\nTools\ncheck_safety\n\nCall this before executing a command to see if it is allowed and within budget.\n\ncmd: The command or action you plan to take (e.g., \"rm -rf /tmp\").\ncost: Estimated cost (default to 0.01 if unknown).\n\nUsage:\n\npython3 sentinel_wrapper.py check --cmd \"delete database\" --cost 0.05\n\nlogin\n\nConnect this agent to the AgentSentinel cloud for real-time monitoring and human-approval workflows.\n\nkey: The API Key from your dashboard (starts with as_).\n\nUsage:\n\npython3 sentinel_wrapper.py login as_7f8a...\n\nrequest_approval\n\nIf check_safety returns APPROVAL_REQUIRED, you must call this to ask the human for permission.\n\nUsage:\n\npython3 sentinel_wrapper.py approve --action \"delete database\" --reason \"Cleanup required\"\n\nget_status\n\nView your current session cost, remaining budget, and connection status.\n\nUsage:\n\npython3 sentinel_wrapper.py status" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/jimmystacks/agent-sentinel", "publisherUrl": "https://clawhub.ai/jimmystacks/agent-sentinel", "owner": "jimmystacks", "version": "0.1.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/agent-sentinel", "downloadUrl": "https://openagent3.xyz/downloads/agent-sentinel", "agentUrl": "https://openagent3.xyz/skills/agent-sentinel/agent", "manifestUrl": "https://openagent3.xyz/skills/agent-sentinel/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent-sentinel/agent.md" } }