Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Judge a coding agent session v1.0.0

Use this resource to judge an agent session or eval result from evidence

New

  • 505 downloads
  • 108 likes
  • 174 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install judge-agent-session-verdict

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent checks controller attestations first, then project guards, code review and the repository's design contract. It returns a pass, fail or inconclusive verdict and names the smallest harness owner to fix. The analysis is read-only and never runs the session content.

Mostly picked by

Updated November 2, 2026

Card for the “Judge a coding agent session” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: arguments, workflow and verdict rules
  • references/criteria-format.md: format of the evaluation criteria

Good fit for

  • You want to review an agent session before accepting its output
  • You need to analyze the result of an eval harness

Not for

    Tags

    • evaluation
    • agent
    • verdict
    • review

    About

    You say

    “Judge this agent session and tell me which harness part to fix.”

    Card for the “Judge a coding agent session” skill

    Skill published by open-mercato under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to judge an agent session or eval result from evidence
    3. Review and adjust the result

    Content preview

    Files

    • agents/openai.yaml0.2 KB
    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/agentic-setup.md4.8 KB
    • references/criteria-format.md2.8 KB
    • references/input-normalization.md2.4 KB
    • references/judge-workflow.md4.5 KB
    • references/report-templates.md2 KB
    • references/rules.md6.7 KB
    • SKILL.md5.3 KB

    Origin and licence

    Listed unmodified

    Author
    open-mercato
    Source
    github.com/open-mercato/skills/tree/002bf5cbf9e9ffe4b56120b4f79080cf61df79d4/skills/om-judge-agent-session
    Licence
    MIT

    Notice

    « om-judge-agent-session » (open-mercato, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.