kdeps-tools-judge_verdict
v1.0.0Settle your review of the candidate output. Must be called exactly once, when your review is complete.
set tools / shelf evals
LLM context: ~82 tokens when loaded (prompt or tool definition)
Where it runs
Part of the tools set, used in workflow and agent mode. What the model is told about each built-in tool: its description, usage notes and parameters. kdeps runs the tool itself.
- the agent loop builds the request
- the tool definitions are sent to the modeltools/judge_verdict
- the model calls a tool
- kdeps runs it
- the result goes back to the model
Loaded by: kdeps (agent loop), /update, /settings, kdeps run, kdeps install, kdeps list, kdeps uninstall, kdeps update
In the code: kdeps (agent loop)agent.RegisterBuiltinToolsagent.definedAs
Install
A kdeps asset: installed with the first-run profile that includes its set, or the first time a command needs it, and updated without a new release.
Pin a version with kdeps install tools/judge_verdict@<version>.
Contents
Settle your review of the candidate output. Must be called exactly once, when your review is complete.
| Parameter | Type | Description |
|---|---|---|
| approved * | boolean | true if the output meets your criteria |
| feedback | string | Required when approved is false: what specifically to fix |
version: 1.0.0
description: Settle your review of the candidate output. Must be called exactly once, when your review is complete.
parameters:
approved:
type: boolean
description: true if the output meets your criteria
required: true
feedback:
type: string
description: 'Required when approved is false: what specifically to fix'
Versions
| Version | Published | Status |
|---|---|---|
| 1.0.0 | 10/11/2026 | active |
Details
- Author
- kdeps
- License
- Apache-2.0
- Latest Version
- 1.0.0
- Published
- 10/11/2026