Agents Lookup

Use cases / Decision models (Jev)

Check a coding agent's claim that the work is done

Before a coding agent may stop, compare what it says it did with a ledger of what it actually ran, with Jev judging the gap.

DifficultyIntermediate
Setup time2-3 hours
CategoryDecision models (Jev)

The use case

Developers using Claude Code or Codex find agents sometimes report a task done without running tests or touching the right files. These hooks log the commands and edits the agent really made and, when it tries to finish, ask whether the claim is backed by a passing check; one also scores the work on quality measures as it goes. An unsupported finish is refused and the agent is told why. The developer still reviews the diff and test output before merging, since a check passing is not the same as the code being right.

Example workflow

  1. Install a Stop or PostToolUse hook in Claude Code or Codex CLI
  2. Log commands run and files changed during the session
  3. At finish, ask Jev whether the done claim is supported by the log
  4. Refuse the finish and return the reason if unsupported
  5. The developer reviews diff and tests before merging

Tools

Risks and guardrails

Sources

Written by Agents Lookup. Credits and official pages for the tools this use case names: