model-committee SKILL.md skillA

model-committee from scdenney/open-science-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add scdenney/open-science-skills/model-committee@git:20261008.697c89f

Pins git:20261008.697c89f in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
scdenney/open-science-skills
Path
codex/model-committee/SKILL.md
Versions recorded
7
Latest version
git:20261008.697c89f, committed Oct 8, 2026
First version recorded
Jul 26, 2026
Size
8,162 bytes
Repository stars
69
License
a license file GitHub does not identify

Run one consequential, contestable decision through a deliberative committee of GPT-6 Astra and Claude Opus, chaired by fable (default), astra, opus, or sol. Not for factual lookups, brainstorming, routine implementation, independent-coder reliability, or final professional judgment. Use when several options are defensible and the two model families should propose, critique, revise, and cross-rank under a predeclared rubric.

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

# Model Committee

Run a GPT-6 Astra member and a Claude Opus member as a deliberating committee, then chair the result. This is not an inter-rater reliability design: independent blind raters measure disagreement, while this committee deliberately exposes each member to the other's argument and returns one decision.

Read [`references/protocol.md`](references/protocol.md) completely before running a committee. It carries the use-case gate, the brief template, the three round contracts, the decision rule, and the `decision.md` schema.

## Pick the chair

One skill, four chairs. Use `$model-committee` with `chair: fable` (the default), `chair: astra`, `chair: opus`, or `chair: sol`. The Claude slash commands `/model-committee-astra`, `-opus`, and `-sol` select these same rows; in Codex they are parameters, not additional skill names. Keep the protocol and the three rounds unchanged. Select the GPT member from the table before creating any member prompt.

| chair | GPT member | Claude member | Chair pin | Use |
|---|---|---|---|---|
| `fable` (default) | `gpt-6-astra`, `xhigh` | `opus`, `high` | `fable`, `high` | Fable synthesizes from outside both member models. |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add scdenney/open-science-skills/model-committee@sha256:7fa3e9a82661653e

The line at the top of this page pins the label git:20261008.697c89f, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_nkjiv64mr2yycpz7.svg)](https://markdownregistry.com/a/art_nkjiv64mr2yycpz7)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 7 versions of this file, between Jul 26, 2026 and Oct 8, 2026, about one every 12 days.

versioncommittedcommitsizeaudit
git:20261008.697c89f latest2026-10-08 697c89f 8,162 BA view · diff
git:20260923.ff955572026-09-23 ff95557 8,072 BA view · diff
git:20260905.39e82762026-09-05 39e8276 8,161 BA view · diff
git:20260902.da5a2632026-09-02 da5a263 9,115 BA view · diff
git:20260808.a34a73d2026-08-08 a34a73d 9,111 BA view · diff
git:20260808.98961c72026-08-08 98961c7 8,933 BA view · diff
git:20260726.ec471db2026-07-26 ec471db 6,206 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8162 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

GitHub

scdenney/open-science-skills · 69 stars · license a license file GitHub does not identify · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_nkjiv64mr2yycpz7
GET https://markdownregistry.com/api/v1/resolve?ref=scdenney/open-science-skills/model-committee
GET https://markdownregistry.com/api/v1/blob/7fa3e9a82661653ef43f64438707ae7f83fad1c6e60ac6f2503d3339acf787f1

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.

More from scdenney/open-science-skills

model-council-voting SKILL.md skill
scdenney/open-science-skills · archive/claude/model-council-voting/SKILL.md · Runs several language models as independent coders on one labeling or discovery task and treats disagreement as data…
git:20261008.eaad168 · audit A · 69 stars
spawn SKILL.md skill
scdenney/open-science-skills · archive/claude/spawn/SKILL.md · Spawns full Claude Code peer sessions in separate terminal panes and git worktrees, real sessions rather than…
git:20261008.eaad168 · audit A · 69 stars
model-council-voting SKILL.md skill
scdenney/open-science-skills · archive/codex/model-council-voting/SKILL.md · Runs several language models as independent coders on the same labeling or discovery task and reads their disagreement…
git:20261008.eaad168 · audit A · 69 stars
spawn SKILL.md skill
scdenney/open-science-skills · archive/codex/spawn/SKILL.md · Spawn full peer Codex or Claude sessions in their own panes and git worktrees — real sessions, not subagents — briefed…
git:20261008.eaad168 · audit A · 69 stars
advisor SKILL.md skill
scdenney/open-science-skills · codex/advisor/SKILL.md · Consult an independent, read-only GPT-6 Astra advisor before committing to a substantive interpretation, approach, or…
git:20261008.c2a591c · audit A · 69 stars
beamer SKILL.md skill
scdenney/open-science-skills · codex/beamer/SKILL.md · House rules and craft for LaTeX Beamer decks (storyboarding, slide prose, frame budgets, layout, XeLaTeX and Korean…
v1.0.0 · audit A · 69 stars
citation-check SKILL.md skill
scdenney/open-science-skills · codex/citation-check/SKILL.md · Audit a manuscript's citations for fabricated sources, DOIs that resolve to the wrong work, in-text and reference-list…
git:20261008.697c89f · audit A · 69 stars
conjoint-cleaning SKILL.md skill
scdenney/open-science-skills · codex/conjoint-cleaning/SKILL.md · Turns a raw Qualtrics conjoint export into analysis-ready long-format data: implementation identification, reshaping…
git:20261008.697c89f · audit A · 69 stars
conjoint-design SKILL.md skill
scdenney/open-science-skills · codex/conjoint-design/SKILL.md · Designs conjoint and factorial-vignette experiments: attributes and restrictions, effective-N power, estimand choice…
git:20261008.cd70e9b · audit A · 69 stars
conjoint-diagnostics SKILL.md skill
scdenney/open-science-skills · codex/conjoint-diagnostics/SKILL.md · Reviews an existing conjoint study for threats to inference and returns severity-ranked findings on design, estimation…
git:20261008.697c89f · audit A · 69 stars
cross-national-design SKILL.md skill
scdenney/open-science-skills · codex/cross-national-design/SKILL.md · Designs multi-country survey experiments: case selection, localization and TRAPD translation, stimulus calibration…
git:20261008.697c89f · audit A · 69 stars
deliverable-intake SKILL.md skill
scdenney/open-science-skills · codex/deliverable-intake/SKILL.md · Turns dictated captures in a deliverable's inbox/ into a proposed planning-wiki diff, classifying and tracing each…
git:20261008.697c89f · audit A · 69 stars

Every file in scdenney/open-science-skills

Other files named model-committee

model-committee SKILL.md skill
scdenney/open-science-skills · plugin/skills/model-committee/SKILL.md · Runs a deliberative two-model committee of GPT-6 Astra and Claude Opus under a selectable chair, Fable by default, with…
git:20261105.dee0bc5 · audit A · 69 stars

Browse by kind, by grade A, or by owner.