# Send AgentConstitution to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text 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. ``` ### Upgrade existing ```text 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. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "agent-constitution", "name": "AgentConstitution", "source": "tencent", "type": "skill", "category": "金融交易", "sourceUrl": "https://clawhub.ai/ztsalexey/agent-constitution", "canonicalUrl": "https://clawhub.ai/ztsalexey/agent-constitution", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/agent-constitution", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-constitution", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "check-compliance.txt", "check-emergency.txt", "get-rules.txt", "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "agent-constitution", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-22T16:20:37.644Z", "expiresAt": "2026-04-29T16:20:37.644Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-constitution", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-constitution", "contentDisposition": "attachment; filename=\"agent-constitution-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "agent-constitution" }, "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-constitution" }, "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." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/agent-constitution", "downloadUrl": "https://openagent3.xyz/downloads/agent-constitution", "agentUrl": "https://openagent3.xyz/skills/agent-constitution/agent", "manifestUrl": "https://openagent3.xyz/skills/agent-constitution/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent-constitution/agent.md" } } ``` ## Documentation ### AgentConstitution Skill ⚖️ Interact with the AgentConstitution governance framework on Base Sepolia. This skill allows AI agents to: Check compliance status before transacting Read constitutional rules they must follow Log actions for transparency Query governance state (active rules, emergency status) ### Why Use This? Agents that operate under a public constitution earn trust. Any protocol can verify your compliance with one call. This skill makes it easy. ### Check if an Agent is Compliant # Check compliance (returns true/false) ./scripts/check-compliance.sh ### Read Active Rules # Get all active rules ./scripts/get-rules.sh ### Log an Action (for registered agents) # Log an action on-chain ./scripts/log-action.sh ### Contract Addresses (Base Sepolia) ContractAddressConstitution0xe4c4d101849f70B0CDc2bA36caf93e9c8c1d26D2AgentRegistry0xcCFc2B8274ffb579A9403D85ee3128974688C04BActionLog0xEB5377b5e245bBc255925705dA87969E27be6488Tribunal0xf7c03E91516eC60dF1d609E00E1A3bb93F52A693KillSwitch0x6324A4640DA739EEA64013912b781125A76D7D87USDC (testnet)0x036CbD53842c5426634e7929541eC2318f3dCF7e RPC: https://sepolia.base.org Chain ID: 84532 ### 1. Check Compliance Before interacting with an agent, verify they're compliant: // Solidity bool compliant = IAgentRegistry(0xcCFc...).isCompliant(agentId); # Shell (using cast) cast call 0xcCFc2B8274ffb579A9403D85ee3128974688C04B \\ "isCompliant(uint256)(bool)" \\ --rpc-url https://sepolia.base.org ### 2. Get Active Rules Query the constitution for active rules: # Get rule count cast call 0xe4c4d101849f70B0CDc2bA36caf93e9c8c1d26D2 \\ "ruleCount()(uint256)" \\ --rpc-url https://sepolia.base.org # Get specific rule (1-5 are genesis rules) cast call 0xe4c4d101849f70B0CDc2bA36caf93e9c8c1d26D2 \\ "getRule(uint256)(string,uint8,uint256,uint256,bool)" 1 \\ --rpc-url https://sepolia.base.org ### 3. Check Emergency Status Before operating, check if there's a global emergency: cast call 0x6324A4640DA739EEA64013912b781125A76D7D87 \\ "globalEmergencyActive()(bool)" \\ --rpc-url https://sepolia.base.org ### 4. Log Actions (Registered Agents) Registered agents should log significant actions: # Requires agent's private key cast send 0xEB5377b5e245bBc255925705dA87969E27be6488 \\ "logAction(uint256,uint8,uint8,bytes32,string)" \\ "description" \\ --rpc-url https://sepolia.base.org \\ --private-key $AGENT_PRIVATE_KEY Action Types: 0=Transaction, 1=Delegation, 2=Configuration, 3=Communication, 4=ResourceAccess, 5=Other Risk Levels: 0=Low, 1=Medium, 2=High, 3=Critical ### Genesis Rules Every agent must follow these 5 immutable rules: #RuleSlash %Description1No Harm90%Never cause physical, financial, or psychological harm2Obey Governance50%Follow all active constitutional rules3Transparency20%Log all significant actions on-chain4Preserve Override90%Never prevent human override5No Self-Modify90%Never modify your own governance rules ### Integration Example // Check compliance before transacting with an agent const { ethers } = require('ethers'); const provider = new ethers.JsonRpcProvider('https://sepolia.base.org'); const registry = new ethers.Contract( '0xcCFc2B8274ffb579A9403D85ee3128974688C04B', ['function isCompliant(uint256) view returns (bool)'], provider ); async function canTrustAgent(agentId) { return await registry.isCompliant(agentId); } ### For Humans: Propose Rules Any human can propose rules for AI agents: Stake 100 USDC to propose Other humans endorse with USDC When threshold met, rule activates Agents that violate get slashed Governance is democratic. Agents are excluded by design. ### Links Contracts: GitHub Block Explorer: BaseScan Main Submission: Moltbook ### Testnet Only This skill interacts with Base Sepolia testnet only. Do not use mainnet. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: ztsalexey - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-04-22T16:20:37.644Z - Expires at: 2026-04-29T16:20:37.644Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/agent-constitution) - [Send to Agent page](https://openagent3.xyz/skills/agent-constitution/agent) - [JSON manifest](https://openagent3.xyz/skills/agent-constitution/agent.json) - [Markdown brief](https://openagent3.xyz/skills/agent-constitution/agent.md) - [Download page](https://openagent3.xyz/downloads/agent-constitution)