p202 goal evaluate

Evaluate definitions against events without writing anything

All commands

p202 CLI reference

Back to the docs

01Run it

Replace the <placeholders> with your own values, or use the builder below.

p202 goal evaluate

02What you get

Pick the shape you need. People get a table. Add --json, --csv or --ndjson for scripts, or -q for ids only. An AI agent gets compact JSON without asking. All output formats

03Build your command

Pick values and the command line writes itself, quoted and ready to paste.

p202 goal evaluate

Set flags below; the command updates as you type.

04Flags

1 flag, plus the global flags every command takes.

FlagWhat it does
--file, -FstringJSON body: goals, subject, events (- for stdin)

05How it works

Sends {"goals", "subject", "events"} — the format of the evaluator vectors in tests/fixtures/app-sdk-contract/goals/ — and prints the outcomes the server's evaluator reaches. Nothing is stored.

06For agents

Running this from an agent

  • Read the same facts as JSON: p202 commands goal evaluate --json.
  • With AI_AGENT, CLAUDECODE or another agent variable set, output is compact JSON and errors arrive on stderr as a JSON envelope with a hint.
  • Exit codes: 0 ok, 1 bad input, 2 auth, 3 network, 4 server error, 5 partial failure.
p202 commands goal evaluate --json
{
  "path": "p202 goal evaluate",
  "use": "evaluate",
  "short": "Evaluate definitions against events without writing anything",
  "long": "Sends {\"goals\", \"subject\", \"events\"} — the format of the evaluator vectors in\ntests/fixtures/app-sdk-contract/goals/ — and prints the outcomes the server's evaluator\nreaches. Nothing is stored.",
  "runnable": true,
  "flags": [
    {
      "name": "file",
      "shorthand": "F",
      "type": "string",
      "default": "",
      "usage": "JSON body: goals, subject, events (- for stdin)",
      "required": false
    }
  ]
}