simmer-judge-board SKILL.md skillA
simmer-judge-board from 2389-research/simmer is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add 2389-research/simmer/simmer-judge-board@git:20260706.3f264f4Pins git:20260706.3f264f4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- 2389-research/simmer
- Path
skills/simmer-judge-board/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260706.3f264f4, committed Jul 6, 2026
- First version recorded
- Mar 23, 2026
- Size
- 18,623 bytes
- Repository stars
- 16
- License
- MIT
Do not invoke directly — dispatched by the simmer orchestrator when JUDGE_MODE is board. Runs a panel of perspective-diverse judges to produce consensus scores and a single ASI; drop-in replacement for simmer-judge used for complex or plateaued artifacts.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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 …
Read the whole file at its exact version.
How to install
mdr add 2389-research/simmer/simmer-judge-board@sha256:1d059423a8e36448The line at the top of this page pins the label git:20260706.3f264f4, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_3te62xzbi6zzfhnl)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Mar 23, 2026 and Jul 6, 2026, about one every 26 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260706.3f264f4 latest | 2026-07-06 | 3f264f4 | 18,623 B | A | view · diff |
| git:20260323.52a50f2 | 2026-03-23 | 52a50f2 | 22,223 B | A | view · diff |
| git:20260323.61cec92 | 2026-03-23 | 61cec92 | 21,973 B | A | view · diff |
| git:20260323.529ee93 | 2026-03-23 | 529ee93 | 28,482 B | A | view · diff |
| git:20260323.4058dc7 | 2026-03-23 | 4058dc7 | 30,603 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (18623 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
2389-research/simmer · 16 stars · license MIT · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_3te62xzbi6zzfhnl GET https://markdownregistry.com/api/v1/resolve?ref=2389-research/simmer/simmer-judge-board GET https://markdownregistry.com/api/v1/blob/1d059423a8e364488ab4d0a7b93eb8cbd012e0d2bcb869df8a15f9173d7bd272
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.