What is ai-council-review?

A review workflow that asks four independent AI models to examine a pull request, plan, or files through the OpenRouter API, then groups agreements and disagreements for a final review.

Use it for high-stakes code reviews, plan reviews, or decisions where one additional opinion is not enough.

It provides several outside opinions when a code change or decision is important or disputed. The material is sent to OpenRouter and other model providers, and the run costs money.

ai-council-review — Skill for Claude Code by eins78

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.

Any agent

npx skills add eins78/agent-skills --skill ai-council-review

Clone the repo

git clone --depth 1 https://github.com/eins78/agent-skills

Made for: Claude Code.

Or install eins78-skills, the plugin that ships this one along with the rest of its 15 skills.

Its marketplace also offers this one on its own, as the plugin ai-council-review — /plugin install ai-council-review after adding the marketplace above.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/eins78/agent-skills/ai-council-review/github.svg)](https://agentmods.dev/skills/eins78/agent-skills/ai-council-review)

Your own site

<a href="https://agentmods.dev/skills/eins78/agent-skills/ai-council-review"><img src="https://agentmods.dev/badge/skills/eins78/agent-skills/ai-council-review/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/eins78/agent-skills/ai-council-review"><img src="https://agentmods.dev/badge/skills/eins78/agent-skills/ai-council-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,203 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.

Model	Per session	Once invoked
Fable 5.1	$0.00140	$0.02203
Opus 5	$0.00070	$0.01102
Sonnet 5	$0.00028	$0.00441
Haiku 4.5	$0.00014	$0.00220

Measured 11d ago against content hash 5b1b4927e78e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ai-council-review 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 11d ago.

The scan reads SKILL.md. This mod also ships 16 executable files (scripts/council.mjs, scripts/lib/budget.mjs, scripts/lib/cluster.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/ai-council-review/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Council Review

Several frontier models review the same material in parallel — blind to each other — via one API (OpenRouter). A dispatch script handles fan-out, cost gating, and clustering; you synthesize, because you can do the one thing the council cannot: verify findings against the actual repository.

This is the heavyweight sibling of ai-review (single model, ~~$0.03). A council run costs real money (~~$0.30–0.90 with default presets). Use it for high-stakes decisions, not routine diffs.

Data leaves the machine — confirm before first dispatch

Everything submitted (diffs, plan docs, file contents) is sent to the OpenRouter API and forwarded to multiple third-party model providers (different companies, different data-retention policies). For private or proprietary code this means unreleased source leaves the machine.

Before the FIRST council run in a session, confirm with your human partner that sending this content to external providers is acceptable — especially in private repos or anything under NDA. Consent given for this repo earlier in this session carries over; do not re-ask per run.
Reduce exposure: review the diff, not the whole tree; never include .env files, credentials, or customer data in the input.
Account-wide tightening: OpenRouter privacy settings (disable logging, restrict to ZDR-eligible providers).

Prerequisites

Node.js >= 20 (node --version)
OPENROUTER_API_KEY exported (get one: https://openrouter.ai/keys). The script reads it from the environment only and never prints it. If it is missing, dispatch exits with code 4 — ask your human partner; do NOT hunt for keys in keychains, dotfiles, or session archives.

CRITICAL rules

Never fabricate or substitute a council opinion. If members fail or quorum is not met, report that and offer the ai-review fallback — do not write "what the model would probably say", and do not pass your own review off as a member's.
Never pass --yes on your own. --yes asserts that your human partner saw the printed cost estimate and approved it in this session. Budget gate refusals (exit 3) are a stop, not an obstacle to route around.
Never skip the synthesis protocol. Raw per-model output is not the deliverable; the verified, dissent-preserving report is.

Read the full file on GitHub · 200 lines

Files

What ships with it

29 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

11d ago First seen · 200 lines · 140 tokens per session scan A 5b1b4927e78e

Subscribe to this mod's changes

ai-council-review is a skill published in the GitHub repository eins78/agent-skills (2 stars, last pushed today), licensed MIT. It adds 140 tokens to every session and 2,203 once invoked, about $0.0007 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 2026-08-31.

Building agents Code review agent-skills claude-code-skills

solid-principles

SOLID principles checklist with Java examples. Use when a class has too many responsibilities, an abstraction leaks, or a dependency points the wrong way, and when the user asks about Single Responsibility, Open/Closed, Liskov, Interface Segregation or Dependency Inversion. For naming, duplication and method length…

decebals/claude-code-java · 73 tokens

architecture-review

Analyze Java project architecture at macro level - package structure, module boundaries, dependency direction, and layering. Use when user asks "review architecture", "check structure", "package organization", or when evaluating if a codebase follows clean architecture principles.

decebals/claude-code-java · 51 tokens

java-code-review

Systematic code review for Java with null safety, exception handling, concurrency, and performance checks. Use when user says "review code", "check this PR", "code review", or before merging changes.

decebals/claude-code-java · 45 tokens

refactoring-patterns

Apply named refactoring transformations to improve code structure without changing behavior. Use when the user mentions "refactor this", "code smells", "extract method", "replace conditional", "technical debt", "move method", "inline variable", "decompose conditional", or "clean up this messy code". Also trigger when…

wondelai/skills · 125 tokens

boundaries

Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.

oliver-kriska/claude-elixir-phoenix · 33 tokens

triage

Triage review findings interactively — approve, skip, or prioritize each issue. Use after /phx:review to filter findings before fixing.

oliver-kriska/claude-elixir-phoenix · 32 tokens