llm-council SKILL.md skillA

llm-council from ffroliva/gflow-cli is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add ffroliva/gflow-cli/llm-council@git:20260828.f286d30

Pins git:20260828.f286d30 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
ffroliva/gflow-cli
Path
skills/llm-council/SKILL.md
Versions recorded
3
Latest version
git:20260828.f286d30, committed Aug 28, 2026
First version recorded
Jul 15, 2026
Size
7,896 bytes
Repository stars
324
License
MIT

Use when a pr-council-review (PR or branch mode) result needs independent corroboration from a different model family before trusting a GREEN verdict — high-stakes, security-sensitive, or architecturally significant reviews where same-model-family Claude subagents might share a blind spot. Also use when the user asks for "external", "second opinion", "cross-model", or names codex/antigravity (`agy`) or another external CLI coding agent alongside a review.

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

# `llm-council` — external-tools review layer

## Overview

Wraps `pr-council-review` (unchanged) and adds a layer of external CLI coding agents (`codex`, plus Antigravity — the `agy` harness) as additional independent reviewers, then folds their verdicts into the same synthesis. Internal Claude subagents are independent per-dimension but share one model family's blind spots — a phrasing choice, a Windows-vs-POSIX nuance, or a syntax error that reads fine to one Claude reviewer reads fine to all of them. A different model family catches a different error distribution. Confirmed live: on one review, external tools caught 6 real, distinct issues (a wording-accuracy bug, a wrong test count, a Windows-only test-triviality nuance, a test-isolation gap, a missing test, a malformed markdown fence) that 12 internal Claude-subagent dispatches (6 dimensions × 2 rounds) had all missed.

## When to Use

- Any `pr-council-review` run (PR# mode or branch mode) where the artifact is high-stakes enough to want a second, differently-biased opinion before calling it GREEN.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ffroliva/gflow-cli/llm-council@sha256:cb25ddec3ea1315a

The line at the top of this page pins the label git:20260828.f286d30, 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_qedvk3z3sdhdhhig.svg)](https://markdownregistry.com/a/art_qedvk3z3sdhdhhig)

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

Versions

The registry has recorded 3 versions of this file, between Jul 15, 2026 and Aug 28, 2026, about one every 22 days.

versioncommittedcommitsizeaudit
git:20260828.f286d30 latest2026-08-28 f286d30 7,896 BA view · diff
git:20260720.7dd66042026-07-20 7dd6604 7,021 BA view · diff
git:20260715.99513392026-07-15 9951339 6,702 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 (7896 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

ffroliva/gflow-cli · 324 stars · license MIT · pushed 2026-10-23 · branch develop

API

GET https://markdownregistry.com/api/v1/artifacts/art_qedvk3z3sdhdhhig
GET https://markdownregistry.com/api/v1/resolve?ref=ffroliva/gflow-cli/llm-council
GET https://markdownregistry.com/api/v1/blob/cb25ddec3ea1315abab83fb3d88bd5fe8053315576b1d256157aba85222a3bc9

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 ffroliva/gflow-cli

AGENTS.md AGENTS.md file
ffroliva/gflow-cli · AGENTS.md
git:20261022.1fa8514 · audit A · 324 stars
CLAUDE.md CLAUDE.md file
ffroliva/gflow-cli · CLAUDE.md
git:20260914.c5d73ba · audit A · 324 stars
llms.txt llms.txt file
ffroliva/gflow-cli · llms.txt
git:20261022.f2e2bba · audit A · 324 stars
gflow-cli SKILL.md skill
ffroliva/gflow-cli · plugins/gflow/skills/gflow-cli/SKILL.md · Use when the user wants to drive Google Flow (Veo image-to-video, Veo text-to-video, Imagen / Nano Banana image…
v1.2 · audit B · 324 stars
video-production SKILL.md skill
ffroliva/gflow-cli · plugins/gflow/skills/video-production/SKILL.md · Use when the user wants a finished video out of gflow rather than a single clip — a scripted scene, a talking-head or…
v2.0 · audit A · 324 stars
changelog SKILL.md skill
ffroliva/gflow-cli · skills/changelog/SKILL.md · Show unreleased changes and last tagged version — insight into recent work.
v1.0 · audit A · 324 stars
check SKILL.md skill
ffroliva/gflow-cli · skills/check/SKILL.md · Auto-fix lint and formatting, then report types and tests. Run before every commit.
v1.0 · audit A · 324 stars
doc-review SKILL.md skill
ffroliva/gflow-cli · skills/doc-review/SKILL.md · Use before cutting any gflow-cli release or after a major documentation change — systematic council-driven audit that…
v1.0 · audit A · 324 stars
gflow-cli SKILL.md skill
ffroliva/gflow-cli · skills/gflow-cli/SKILL.md · Use when the user wants to drive Google Flow (Veo image-to-video, Veo text-to-video, Imagen / Nano Banana image…
v1.2 · audit B · 324 stars
issue-assessment SKILL.md skill
ffroliva/gflow-cli · skills/issue-assessment/SKILL.md · Use when triaging a GitHub issue for gflow-cli — a reporter's bug claim, a freshly-filed issue, or deciding whether and…
v1.0 · audit A · 324 stars
issue-resolve SKILL.md skill
ffroliva/gflow-cli · skills/issue-resolve/SKILL.md · Use when an assessed gflow-cli issue (verdict CONFIRMED-BUG or LIKELY-BUG) has localized, verifiable scope and should…
v1.0 · audit A · 324 stars
known-issues SKILL.md skill
ffroliva/gflow-cli · skills/known-issues/SKILL.md · Surface open known issues. Call before touching auth, reCAPTCHA, or anything previously flagged.
v1.0 · audit A · 324 stars

Every file in ffroliva/gflow-cli

Other files named llm-council

llm-council SKILL.md skill
rohitg00/pro-workflow · skills/llm-council/SKILL.md · Provider-agnostic multi-LLM deliberation. Three phases — independent responses, cross-model anonymized ranking…
git:20260929.86d5f27 · audit A · 2,922 stars
llm-council SKILL.md skill
pranav-nexus/antigravity-skill-porter · examples/llm-council/skills/llm-council/SKILL.md · Run high-stakes questions, architectural decisions, product dilemmas, or major tradeoffs through a council of 5…
git:20260907.8fba83e · audit A · 6 stars
llm-council SKILL.md skill
jzkk720/cubecloud-skills-bundle-kit · upstream/llm-council/SKILL.md · Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each…
git:20260817.87a6498 · audit A · 4 stars

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