llm-council: Skill for Claude Code

.github/skills/council-review/SKILL.md

council-review is a skill for Claude Code from amiable-dev/llm-council. It costs 50 tokens per session (1,069 once invoked), scanned A, original, MIT.

A multi-model code-review workflow that asks several AI reviewers to assess a change using a structured rubric. A pull request is a proposed code change submitted for review before it is merged.

In plain words
What is it for?
Use it to review pull requests, inspect implementation quality, and focus feedback on areas such as security or performance.
Why use it?
It gives broader feedback on a change and makes review results more consistent by recording the exact code snapshot, files, or diff being examined.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is amiable-dev/llm-council's own configuration. It tells Claude Code how to work on llm-council itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llm-council configures →

Reuse

Borrowing it

Nothing to install: this file belongs to amiable-dev/llm-council. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/amiable-dev/llm-council/master/.github/skills/council-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/amiable-dev/llm-council

Made for: Claude Code.

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 council-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/amiable-dev/llm-council/council-review/github.svg)](https://agentmods.dev/skills/amiable-dev/llm-council/council-review)
Your own site
<a href="https://agentmods.dev/skills/amiable-dev/llm-council/council-review"><img src="https://agentmods.dev/badge/skills/amiable-dev/llm-council/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.

agentmods 80×15 button for council-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/amiable-dev/llm-council/council-review"><img src="https://agentmods.dev/badge/skills/amiable-dev/llm-council/council-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,069 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00050 $0.01069
Opus 5 $0.00025 $0.00535
Sonnet 5 $0.00010 $0.00214
Haiku 4.5 $0.00005 $0.00107

Measured 10d ago against content hash a8b1e6dd179e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

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 10d 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.

.github/skills/council-review/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Council Code Review Skill

Get multiple AI perspectives on code changes with structured, actionable feedback.

When to Use

  • Review pull requests before merging
  • Get code quality feedback on implementations
  • Identify potential issues across multiple dimensions
  • Validate changes against coding standards

Workflow

  1. Prepare Input: Provide file paths or git diff
  2. Invoke Review: Call mcp:llm-council/verify with code-review rubric
  3. Process Feedback: Receive structured scores and issue list
  4. Address Issues: Fix blocking issues before proceeding

Parameters

Parameter Type Default Description
snapshot_id string required Git commit SHA for reproducibility
file_paths list null List of files to review (full file analysis)
git_diff string null Unified diff format for change-focused review
rubric_focus string null Focus area: "Security", "Performance", etc.
tier string "high" Confidence tier: "quick", "balanced", "high", "reasoning"

Tier Selection Guide

Tier Use When Timeout
balanced Routine code reviews ~90s
high Quality-critical reviews (default) ~180s
reasoning Complex architectural or security reviews ~600s

Input Formats

Supports both:

  • file_paths: List of files to review (full file analysis)
  • git_diff: Unified diff format for change-focused review
  • snapshot_id: Git commit SHA (required for reproducibility)

Rubric (ADR-016)

Dimension Weight Focus
Accuracy 35% Correctness, no bugs, logic errors
Completeness 20% All requirements addressed
Clarity 20% Readable, maintainable code
Conciseness 15% No unnecessary complexity
Relevance 10% Addresses stated requirements

Output Schema

{
  "verdict": "pass|fail|unclear",
  "confidence": 0.82,
  "rubric_scores": {
    "accuracy": 7.5,
    "completeness": 8.0,
    "clarity": 9.0,
    "conciseness": 8.5,
    "relevance": 9.0
  },
  "blocking_issues": [
    {
      "severity": "major",
      "file": "src/api.py",
      "line": 42,
      "message": "Missing input validation"
    }
  ],
  "rationale": "Overall, the code is well-structured...",
  "partial": false,
  "timeout_fired": false,
  "completed_stages": ["stage1", "stage2", "stage3"]
}

Read the full file on GitHub · 131 lines

Files

What ships with it

1 file 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.

  1. 10d ago First seen · 131 lines · 50 tokens per session scan A a8b1e6dd179e

Subscribe to this mod's changes

council-review is a skill published in the GitHub repository amiable-dev/llm-council (41 stars, last pushed 9d ago), licensed MIT. It adds 50 tokens to every session and 1,069 once invoked, about $0.0003 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

review

Assess the blast radius of a change and review a diff — what it touches, what could break, which tests to run, and the prior decisions behind it. Use before a refactor, rename, or signature change, and when reviewing a pull request or your own uncommitted diff.

TheWinci/mimirs · 60 tokens

live-audit

Audit steam-games-mcp — build/test/lint gate, live MCP tool edge-case sweep (input validation, SteamID64/vanity/appid edge cases, key-gating), and source-level code review. Use when asked to test/audit the published or just-fixed steam-games-mcp package, hunt for bugs/edge cases, or repeat "the same kind of testing as…

Grinv/steam-games-mcp · 83 tokens

tool-description-check

Self-check a new or edited MCP tool description/field .describe() text before committing — verify every behavioral claim against live testing or source, check for contradictions with sibling tools, and score against Glama's Tool Definition Quality Score (TDQS) rubric. Use whenever a tool description or schema field…

Grinv/steam-games-mcp · 76 tokens

java-best-practices

Java coding best practices. Use when writing or reviewing Java code (17+). Covers modern features, error handling, and patterns.

Taoidle/plan-cascade · 32 tokens

tool-defs-analysis

Read-only audit of MCP definition language across an existing surface — tools, resources, prompts, server instructions. Walks every definition file and checks 16 categories the LLM reads to decide whether and how to call: voice & tense, internal leaks, audience leaks, defaults, recovery hints, field descriptions…

cyanheads/brapi-mcp-server · 177 tokens

code-simplifier

Post-session code review and cleanup against a working tree of changes. Analyzes git diff to simplify, consolidate, and align changed code with the existing codebase — modernize syntax, remove unnecessary complexity, consolidate duplicated logic, catch efficiency issues. Use after a substantive working session, or…

cyanheads/pubchem-mcp-server · 124 tokens