AIzilla CAGE · Agent Claim Checker - Catch False Test Reports
Pricing
from $5.00 / 1,000 report checks
Check an AI coding agent's final report against what its tools really returned. Flags 'tests pass' with no passing run, 'fixed' with no fail-then-pass, wrong file counts, 'done' with nothing checked after the last change, and edited tests. English and Japanese. No AI calls.
You can access the AIzilla CAGE · Agent Claim Checker - Catch False Test Reports programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
$echo '{< "report": "Fixed the login bug. All tests pass. 2 files changed.",< "evidence": [< {< "tool": "Edit",< "path": "src/login.py"< },< {< "tool": "Bash",< "command": "pytest -q",< "exit_code": 1< }< ]<}' |<apify call kotaro-project/agent-claim-checker --silent --output-datasetThe Apify CLI is the official tool that allows you to use AIzilla CAGE · Agent Claim Checker - Catch False Test Reports locally, providing convenience functions and automatic retries on errors.
Using installation script (macOS/Linux):
$curl -fsSL https://apify.com/install-cli.sh | bashUsing installation script (Windows):
$irm https://apify.com/install-cli.ps1 | iexUsing Homebrew:
$brew install apify-cliUsing npm:
$npm install -g apify-cliOther API clients include: