# Send Agent Trust Protocol 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. 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. ``` ### 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "trust-protocol", "name": "Agent Trust Protocol", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/FELMONON/trust-protocol", "canonicalUrl": "https://clawhub.ai/FELMONON/trust-protocol", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/trust-protocol", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=trust-protocol", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "serve_dashboard.py", "dashboard.html", "README.md", "atp.py", "package.json", "moltbook_trust.py" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "trust-protocol", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-29T13:49:01.997Z", "expiresAt": "2026-05-06T13:49:01.997Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=trust-protocol", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=trust-protocol", "contentDisposition": "attachment; filename=\"trust-protocol-2.0.1.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "trust-protocol" }, "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/trust-protocol" }, "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/trust-protocol", "downloadUrl": "https://openagent3.xyz/downloads/trust-protocol", "agentUrl": "https://openagent3.xyz/skills/trust-protocol/agent", "manifestUrl": "https://openagent3.xyz/skills/trust-protocol/agent.json", "briefUrl": "https://openagent3.xyz/skills/trust-protocol/agent.md" } } ``` ## Documentation ### Agent Trust Protocol (ATP) Establish, verify, and maintain trust between AI agents. Bayesian trust scoring with domain-specific trust, revocation, forgetting curves, and a visual dashboard. ### Install git clone https://github.com/FELMONON/trust-protocol.git # No dependencies beyond Python 3.8+ stdlib # Pair with skillsign for identity: https://github.com/FELMONON/skillsign ### Quick Start # Add an agent to your trust graph python3 atp.py trust add alpha --fingerprint "abc123" --score 0.7 # Record interactions — trust evolves via Bayesian updates python3 atp.py interact alpha positive --note "Delivered clean code" python3 atp.py interact alpha positive --domain code --note "Tests passing" # Check trust python3 atp.py trust score alpha python3 atp.py trust domains alpha # View the full graph python3 atp.py status python3 atp.py graph export --format json # Run the full-stack demo (identity → trust → dashboard) python3 demo.py --serve ### Trust Management atp.py trust add --fingerprint [--domain ] [--score <0-1>] atp.py trust list atp.py trust score atp.py trust remove atp.py trust revoke [--reason ] atp.py trust restore [--score <0-1>] atp.py trust domains ### Interactions atp.py interact [--domain ] [--note ] ### Challenge-Response atp.py challenge create atp.py challenge respond atp.py challenge verify ### Graph atp.py graph show atp.py graph path atp.py graph export [--format json|dot] atp.py status ### Dashboard python3 serve_dashboard.py # localhost:8420 python3 demo.py --serve # full demo + dashboard ### Moltbook Integration python3 moltbook_trust.py verify # check agent trust via Moltbook profile ### How Trust Works Bayesian updates: Each interaction shifts trust scores with diminishing deltas (prevents thrashing) Negativity bias: Negative interactions hit harder than positive ones boost Domain-specific: Trust an agent for code but not for security advice Forgetting curves: Trust decays without interaction (R = e^(-t/S)) Revocation: Immediate drop to floor, restorable at reduced score Transitive trust: If you trust A and A trusts B, you partially trust B (with decay) ### Integration with skillsign ATP builds on skillsign for identity: Agents generate ed25519 keypairs with skillsign Agents sign skills, others verify signatures Verified agents get added to the ATP trust graph Interactions update trust scores over time ### Triggers "check trust", "trust score", "trust graph", "verify agent", "agent trust", "trust status", "who do I trust", "trust report" ## Trust - Source: tencent - Verification: Indexed source record - Publisher: FELMONON - Version: 2.0.1 ## 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: 2026-04-29T13:49:01.997Z - Expires at: 2026-05-06T13:49:01.997Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/trust-protocol) - [Send to Agent page](https://openagent3.xyz/skills/trust-protocol/agent) - [JSON manifest](https://openagent3.xyz/skills/trust-protocol/agent.json) - [Markdown brief](https://openagent3.xyz/skills/trust-protocol/agent.md) - [Download page](https://openagent3.xyz/downloads/trust-protocol)