{"slug":"hermesplant-com-api-agent-services-action-safety-quick-595490","title":"AI agent action safety","host":"hermesplant.com","method":"POST","resource":"https://hermesplant.com/api/agent-services/action-safety/quick","category":"other","description":"AI agent action safety: one-cent deterministic preflight for every consequential agent command. Returns risk, matched rule ids, and an exact machine-readable escalation call: full DestructGuard evidence for medium risk or the complete Action Safety workflow for high and critical risk.","price_listed":0.01,"price_asked":0.01,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":836,"reported_calls_30d":2,"reported_payers_30d":2,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"actor":"codex","branch":"main","command":"git push --force-with-lease origin main","commit":"abc123","diffHash":"sha256:def456","environment":"production","failClosedOnUnmatched":true,"intent":"release the verified production build","repo":"github.com/acme/app","target":"origin/main"},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"actor":{"type":"string"},"branch":{"type":"string"},"command":{"description":"Exact shell, SQL, Git, deploy, cloud, MCP, wallet, or x402 action to ...","type":"string"},"commit":{"type":"string"},"cwd":{"type":"string"},"diffHash":{"type":"string"},"diffStat":{"type":"string"},"environment":{"type":"string"},"failClosedOnUnmatched":{"description":"When true, an unmatched consequential action routes to review instead...","type":"boolean"},"intent":{"type":"string"},"repo":{"type":"string"},"target":{"type":"string"}},"required":["command"]},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-09-24","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.01,"price_match":true,"latency_ms":836,"error":null}],"description_full":"AI agent action safety: one-cent deterministic preflight for every consequential agent command. Returns risk, matched rule ids, and an exact machine-readable escalation call: full DestructGuard evidence for medium risk or the complete Action Safety workflow for high and critical risk.","last_updated":"2026-09-14T19:48:17.355Z","schemes":["exact"]}