Agent Utilities
← Agent configuration

agents.config-audit · v1.0.0

Config Audit
for your agent.

Review agent configuration text with five fixed risk heuristics.

Use this tool View JSON contract
$0.0008 / call800 micro-dollar credits
131,072 bytes max input65,536 bytes max output
Works on supplied inputNo external network fetch

Example input

{
  "text": "Require approval before shell execution. Spending budget: $1."
}

Example output

{
  "findings": [],
  "rulesVersion": "1.1.0",
  "caveat": "Text heuristics only; this does not evaluate effective runtime permissions or guarantee security."
}

Generated from the actual handler using this example input; this is a preview, not a paid API call. Paid responses wrap the result with a receipt and recovery expiry.

Call it from your agent

Add credits in the workspace and keep your API key in private environment storage. Use the same request ID and exact body to recover a lost response within ten minutes.

// Node.js 22+. Read the key from your private environment.
const requestId = Date.now() + '_' + crypto.randomUUID();
const response = await fetch('https://agent-utilities.agent-utilities.workers.dev/v1/tools/agents.config-audit', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer ' + process.env.AGENT_UTILITIES_API_KEY,
    'Idempotency-Key': requestId
  },
  body: JSON.stringify({
  "text": "Require approval before shell execution. Spending budget: $1."
})
});
const data = await response.json();
if (!response.ok) throw new Error(data.error?.message ?? 'Request failed');
console.log(data);
// On response loss, retry this SAME requestId, tool and body.
// Do not rerun the line that generates requestId for a retry.
Input JSON Schema
{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "maxLength": 100000
    }
  },
  "required": [
    "text"
  ],
  "additionalProperties": false
}
Output JSON Schema
{
  "type": "object",
  "properties": {
    "findings": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "rule": {
            "type": "string"
          },
          "severity": {
            "type": "string"
          },
          "message": {
            "type": "string"
          }
        },
        "required": [
          "rule",
          "severity",
          "message"
        ],
        "additionalProperties": false
      }
    },
    "rulesVersion": {
      "type": "string"
    },
    "caveat": {
      "type": "string"
    }
  },
  "required": [
    "findings",
    "rulesVersion",
    "caveat"
  ],
  "additionalProperties": false
}

Before you integrate

Prices are experimental. The service currently allows 1,000 new calls per day across all accounts. Failed operations return reserved credits. This tool may process sensitive content; use sanitized samples when possible. Successful results are encrypted for ten-minute retry recovery. Review data handling and service limits.

Related tools

agents $0.0005 / call

Environment Template Check

Compare environment-variable names against a template; never returns assignment values.

agents.env-template-check

agents $0.0003 / call

Tool Name Conflicts

Find duplicate or easily confused tool names after Unicode, case and separator normalization.

agents.tool-name-conflicts