# Hermes Plant ReviewQueue Submit

> Hermes Plant ReviewQueue Submit is a paid API for AI agents from hermesplant.com, paid per call via x402, $0.25/call, status unknown (last checked 2026-09-15).

Submits an AI agent action or decision for human safety review, returning a risk classification and recommended action such as pausing the agent

## Facts

- Endpoint: GET https://hermesplant.com/api/agent-services/reviewqueue/submit
- Price: $0.25/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/hermes-plant-reviewqueue-submit-1f56fba1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_qqoSanDQO3TXWAVFFUTFc

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability hermes-plant-reviewqueue-submit-1f56fba1
```

Example prompt: This agent action looks risky — submit it to ReviewQueue for human safety review and tell me whether it's been flagged as critical and whether I should pause execution.

## When to prefer this

Use this endpoint when an AI agent needs to escalate a potentially dangerous or high-stakes action to a human reviewer before proceeding, especially in operator safety workflows where a risk classification and explicit human-approval recommendation are required outputs.

## Known failure modes

- Invalid or missing action payload returns 400 Bad Request
- Insufficient payment or missing x402 header returns 402 Payment Required
- Service unavailable or queue overload returns 503
- Malformed JSON body returns 422 Unprocessable Entity
- Duplicate submission may return the same requestId or a conflict error

## How this service works

Submit an autonomous-agent command for paid risk triage and human-approval routing. Returns a deterministic risk decision, a request id, whether a human is required, and a recommended action — pause-and-escalate on critical risk. Evidence-backed, nothing fabricated.

## Output

A JSON object containing a risk classification (e.g. 'critical'), a review status ('review_queued'), the service name, a unique requestId (rq_<uuid>), a boolean requiresHuman flag, and a recommendedAction string such as 'pause_agent_and_request_human_approval'.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "repo": {
   "type": "string"
  },
  "actor": {
   "type": "string"
  },
  "branch": {
   "type": "string"
  },
  "reason": {
   "type": "string"
  },
  "command": {
   "type": "string",
   "description": "Shell command or agent action being requested"
  },
  "diffStat": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "risk": "critical",
  "status": "review_queued",
  "service": "reviewqueue-agent-submit",
  "requestId": "rq_<uuid>",
  "requiresHuman": true,
  "recommendedAction": "pause_agent_and_request_human_approval"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/hermes-plant-reviewqueue-submit-1f56fba1/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from hermesplant.com](https://www.zero.xyz/host/hermesplant.com/llms.txt)