# ClaudeBot Access Audit

> ClaudeBot Access Audit is a paid API for AI agents from agentreadiness.halowerk.com, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-14).

Passively audits a public URL or domain to evaluate whether ClaudeBot (Anthropic's web crawler) is permitted or blocked based on observable public evidence.

## Facts

- Endpoint: POST https://agentreadiness.halowerk.com/v1/claudebot-access-audit?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/claudebot-access-audit-a1d3bcf8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_k4ohDZ1AR58b8LoNZoeXB

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 claudebot-access-audit-a1d3bcf8 -d '<json body>'
```

Example prompt: Can you check whether ClaudeBot is allowed to crawl example.com — I want to see the current robots.txt evidence, the verdict, and what action I should take if it's blocked?

## When to prefer this

Use this endpoint specifically when you need to determine ClaudeBot's (Anthropic's crawler) access status on a given site, as opposed to other bot audits (GPTBot, CCBot, PerplexityBot). It is ideal for site owners preparing for AI-era SEO, developers debugging why Claude lacks knowledge of their content, or monitoring pipelines that need per-bot access verdicts without active testing or login attempts.

## Known failure modes

- Target URL unreachable or returns non-2xx — audit cannot retrieve evidence
- Malformed or missing robots.txt — observation reflects absence of policy
- Domain normalizes incorrectly if bare domain lacks HTTPS support
- Ambiguous or conflicting directives in robots.txt may produce uncertain verdict
- Rate limiting or firewall on target may block the passive fetch

## How this service works

ClaudeBot access audit fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

## Output

Returns a structured report including: the observed public evidence (e.g. robots.txt rules), the evaluated criterion and threshold, a pass/fail verdict, the exact evidence source URL, known limitations of the passive check, and a mode-specific recommended action. No login, payload injection, or active exploitation is performed.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "target": {
   "type": "string",
   "maxLength": 2048,
   "minLength": 3,
   "description": "Public HTTP(S) URL or domain to inspect. A bare domain is normalized to HTTPS."
  },
  "context": {
   "type": "object",
   "description": "Optional non-secret correlation labels returned unchanged only in the request lifecycle.",
   "maxProperties": 12,
   "additionalProperties": {
    "type": [
     "string",
     "number",
     "boolean",
     "null"
    ]
   }
  },
  "baseline": {
   "type": [
    "object",
    "null"
   ],
   "description": "Optional baseline returned by a previous snapshot call.",
   "additionalProperties": true
  },
  "compare_url": {
   "type": "string",
   "maxLength": 2048,
   "minLength": 3,
   "description": "Optional public comparison URL. Used by change and monitoring services."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/claudebot-access-audit-a1d3bcf8/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentreadiness.halowerk.com](https://www.zero.xyz/host/agentreadiness.halowerk.com/llms.txt)