llm-council

llm-council is a skill for Claude Code, Codex from ffroliva/gflow-cli. It costs 101 tokens per session (1,836 once invoked), scanned A, original, MIT.

An additional review layer for pull requests or branches, using coding agents from a different model family to independently check an existing review. It is intended for changes where missing a problem would matter.

In plain words
What is it for?
Use it to corroborate high-stakes, security-sensitive, or architecturally important code reviews after a standard review has produced a result.
Why use it?
Reviewers from the same model family can share blind spots. A separate reviewer can catch issues that the first review missed before a change is trusted.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/ffroliva/gflow-cli/llm-council
Any agent
npx skills add ffroliva/gflow-cli --skill llm-council
Clone the repo
git clone --depth 1 https://github.com/ffroliva/gflow-cli

Made for: Claude Code, Codex.

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 llm-council

README.md
[![agentmods](https://agentmods.dev/badge/skills/ffroliva/gflow-cli/llm-council.svg)](https://agentmods.dev/skills/ffroliva/gflow-cli/llm-council)
Your own site
<a href="https://agentmods.dev/skills/ffroliva/gflow-cli/llm-council"><img src="https://agentmods.dev/badge/skills/ffroliva/gflow-cli/llm-council.svg" alt="Measured on agentmods" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,836 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00101 $0.01836
Opus 5 $0.00051 $0.00918
Sonnet 5 $0.00020 $0.00367
Haiku 4.5 $0.00010 $0.00184

Measured 5d ago against content hash cb25ddec3ea1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

llm-council 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 5d 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/llm-council/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.
  • Not needed for a quick spot-check or draft iteration — use /review (single-agent) for that; pr-council-review alone for a normal-stakes PR.

Quick Reference — Tiers

Tier Internal (pr-council-review) External tools
small (default) ✅ full dimension council none — identical to running pr-council-review directly
medium codex
high codex + Antigravity (agy)

Tier controls tool breadth, not review rounds. Fix → re-verify → repeat until GREEN (or a round cap) happens at every tier — that's how council review works, not a tier knob.

Tool Registry

Fixed, tested invocation recipes. Do not improvise a command for a listed tool — the "obvious" invocation is often a trap (see codex below).

codex

  • NEVER codex review. Its built-in prompt has gotten stuck in a self-inflicted loop reading skill files via a malformed PowerShell command, then retrying the identical broken command for 20+ minutes with zero progress. Confirmed reproducible on a clean retry.
  • Use: codex exec -s read-only -C <absolute-repo-dir> --skip-git-repo-check "<direct, fully self-contained prompt>".
  • Probe: codex --version (near-instant; confirms binary health only, not auth/quota).
  • Timeout budget: real calls run 10-20 min at default (xhigh) reasoning effort. Always background it — never block synchronously.
  • Orphan risk: a killed/timed-out codex exec can leave codex.exe / codex-code-mode-host.exe / sandbox-helper processes running on Windows. After any kill, verify via tasklist/ps that the named PIDs are actually gone before retrying — a retry racing an orphan still writing the same output path silently corrupts the result.

Read the full file on GitHub · 72 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. 5d ago First seen · 72 lines · 101 tokens per session scan A cb25ddec3ea1

Subscribe to this mod's changes

llm-council is a skill published in the GitHub repository ffroliva/gflow-cli (156 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 1,836 once invoked, about $0.0005 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