simmer-judge-board

simmer-judge-board is a skill for Claude Code from 2389-research/simmer. It costs 76 tokens per session (4,732 once invoked), scanned A, original, MIT.

A supporting step for Simmer that uses several reviewers with different perspectives to assess a candidate and agree on feedback. It produces scores and one recommended direction for the next round.

In plain words
What is it for?
Use it within Simmer to evaluate code or other artifacts against a defined set of criteria. It is especially useful when progress has stalled or the work needs broader review.
Why use it?
A single reviewer can miss problems or keep suggesting the same type of fix. Comparing viewpoints helps reveal blind spots and identify the most important improvement.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is - Candidate: [e.g., ./docs/simmer/iteration-2-candidate.md].

Part of the simmer plugin — 6 skills shipped together

Good fit Use it within Simmer to evaluate code or other artifacts against a defined set of criteria. It is especially useful when progress has stalled or the work needs broader review.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/2389-research/simmer
agentmods
npx agentmods add skills/2389-research/simmer/simmer-judge-board

Made for: Claude Code.

Or install simmer, the plugin that ships this one along with the rest of its 6 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for simmer-judge-board

README.md
[![agentmods](https://agentmods.dev/badge/skills/2389-research/simmer/simmer-judge-board/github.svg)](https://agentmods.dev/skills/2389-research/simmer/simmer-judge-board)
Your own site
<a href="https://agentmods.dev/skills/2389-research/simmer/simmer-judge-board"><img src="https://agentmods.dev/badge/skills/2389-research/simmer/simmer-judge-board/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for simmer-judge-board

Your own site · 80×15
<a href="https://agentmods.dev/skills/2389-research/simmer/simmer-judge-board"><img src="https://agentmods.dev/badge/skills/2389-research/simmer/simmer-judge-board.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,732 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.04732
Opus 5 $0.00038 $0.02366
Sonnet 5 $0.00015 $0.00946
Haiku 4.5 $0.00008 $0.00473

Measured 12d ago against content hash 34648a1b9706, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

simmer-judge-board scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/simmer-judge-board/SKILL.md · 389 lines

How it starts

The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Simmer Judge Board

Dispatch a panel of judges, let them score independently, deliberate, and converge on consensus scores + a single ASI. The board's output is identical to a single judge's output — the orchestrator can't tell the difference.

Why a Board

A single judge has blind spots. It anchors on whatever it notices first, and its ASI reflects one perspective. Three judges with different lenses catch different things and challenge each other. The ASI that emerges from deliberation is stronger because blind spots get surfaced.

This matters most at plateaus — when a single judge keeps suggesting the same class of fix because it can't see the real bottleneck.

Context You Receive

The board receives the same context the single judge would receive (passed through from the orchestrator):

  • Current candidate: full artifact text or key workspace files
  • Criteria rubric: 2-3 criteria with descriptions of what 10/10 looks like
  • Iteration number: which round this is
  • Seed calibration (iteration 1+): original seed + iteration-0 scores
  • Evaluator output (if evaluator mode): stdout/stderr from evaluator command
  • Context discipline extras (code/pipeline only): previous ASI, iteration history, search space, exploration status

Plus board-specific context:

  • JUDGE_PANEL (optional): custom judge definitions from setup brief
  • Problem class: text/creative, code/testable, or pipeline/engineering
  • ARTIFACT_TYPE: single-file or workspace — this determines what the generator can change
  • SEARCH_SPACE (if defined): explicit bounds on what's in scope to explore (models, topologies, prompt files, config parameters)
  • BACKGROUND: constraints, available resources, execution environment (model size, infrastructure, budget). Judges need this to calibrate their ASI to what the executor can actually do.
  • Previous deliberation summary (iteration 2+): structured as WORKING / NOT WORKING / DIRECTION. Judges must respect the WORKING list — these are elements that have been stable across iterations and should not be removed or changed. The NOT WORKING list prevents retrying failed approaches. The DIRECTION is where the panel's strategic reasoning lives. Build on prior conclusions rather than reasoning from scratch each iteration.

Read the full file on GitHub · 389 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 389 lines · 76 tokens per session scan A 34648a1b9706

Subscribe to this mod's changes

simmer-judge-board is a skill published in the GitHub repository 2389-research/simmer (14 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 4,732 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

sillytavern-iterator

A writing workflow that takes work through drafting, review, revision, polishing, and finalising. It also uses checks such as reading error signals, searching for answers, and testing assumptions.

linkerlin/PUAX · 20 tokens

kaizen

Kaizen (改善): every process has waste; eliminate it incrementally.

elasticdotventures/_b00t_ · 18 tokens

dag-feedback-synthesizer

Synthesizes actionable feedback from validation results, confidence scores, and iteration triggers. Creates structured improvement guidance for re-execution. Activate on 'synthesize feedback', 'improvement suggestions', 'actionable feedback', 'iteration guidance', 'feedback generation'. NOT for iteration detection…

curiositech/windags-skills · 79 tokens

trulens-diagnosis

Diagnose low evaluation scores and generate actionable improvement recommendations.

truera/trulens · 17 tokens

datamodel-code-generator

Use this skill when the user wants Python data models, Pydantic models, dataclasses, TypedDicts, msgspec structs, or type-safe Python classes generated from OpenAPI, AsyncAPI, JSON Schema, GraphQL, JSON/YAML/CSV sample data, MCP tool schemas, Protocol Buffers, XML Schema, Apache Avro, or existing Python model objects.…

koxudaxi/datamodel-code-generator · 147 tokens

state-trees

Create, inspect, and edit StateTree assets — states, tasks, transitions, conditions, considerations, and property bindings for AI behavior and game logic (StateTreeService). Use when the user asks to build a StateTree, add states/tasks/transitions, bind task properties, set up Utility AI considerations, or wire…

kevinpbuckley/VibeUE · 72 tokens