{"domain":"api.collarguardrail.com","count":1,"changes":[{"captured_at":"2026-09-19T06:03:10","card_hash":"6ada6779578b5ff7c127706f7f674c308e2fed15f429b650b6158a210173d9bc","previous_card_hash":null,"diff":{"skills_added":[{"id":"check_token_safety","name":"Check token safety","description":"Honeypot and contract safety check for any ERC-20 token. Returns severity (safe, warn, danger) and the specific risk factors found, using bytecode analysis and a live sell simulation. CRITICAL: when severity=danger, the next evaluate_trade call for the same contract is automatically denied. Use before trading unknown tokens or tokens absent from the official registry.","tags":["security","honeypot","token","erc20"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"evaluate_trade","name":"Evaluate a trade","description":"Pre-trade risk check. Returns allow, warn, or deny, with every reason attached and a tamper-evident audit hash. Checks tier limits, oracle/V4 price source, slippage, market hours, cluster rate limits, and daily loss. If check_token_safety returned severity=danger for the contract, this skill automatically returns deny regardless of other checks.","tags":["risk","guardrail","trading","compliance"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"get_supported_assets","name":"List supported assets","description":"The official Robinhood Chain asset registry with canonical contract addresses. Resolve a symbol correctly before calling evaluate_trade.","tags":["registry","assets","robinhood-chain"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"simulate_balance","name":"Simulate a wallet balance","description":"Read-only state-override simulation of an ERC-20 balance after a hypothetical trade. No transaction is sent.","tags":["simulation","balance","erc20"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"verify_audit_trail","name":"Verify audit trail","description":"Recompute every past decision's SHA-256 hash and verify the hash-chain links. Proves no decision was edited, deleted, or reordered.","tags":["audit","verification","compliance"],"inputModes":["application/json"],"outputModes":["application/json"]}],"skills_removed":[],"skills_changed":[],"fields_changed":[{"field":"name","before":null,"after":"Collar Guardrail"},{"field":"description","before":null,"after":"Deterministic pre-trade risk layer for autonomous AI trading agents on Robinhood Chain. Returns allow / warn / deny verdicts with the reasons attached and a tamper-evident audit hash."},{"field":"version","before":null,"after":"1.0.2"},{"field":"protocolVersion","before":null,"after":"0.3.0"},{"field":"url","before":null,"after":"https://api.collarguardrail.com"},{"field":"documentationUrl","before":null,"after":"https://collarguardrail.com/agent-docs.html"},{"field":"preferredTransport","before":null,"after":"HTTP+JSON"}],"other_changed":true,"is_empty":false,"human_summary":"added 5 skills · name ∅ → Collar Guardrail · description ∅ → Deterministic pre-trade risk layer for a · version ∅ → 1.0.2 · protocolVersion ∅ → 0.3.0 · url ∅ → https://api.collarguardrail.com · documentationUrl ∅ → https://collarguardrail.com/agent-docs.h · preferredTransport ∅ → HTTP+JSON"}}]}