review

review is a skill for Claude Code from raine/consult-llm. It costs 40 tokens per session (2,275 once invoked), scanned A, original, MIT.

A facilitated design session for turning a rough idea into a more settled plan through questions, several AI suggestions, user choice, and optional critique.

In plain words
What is it for?
It helps explore product or technical concepts, compare proposed approaches, refine one with the user, and save the resulting design.
Why use it?
It gives structure to unclear ideas and exposes different possible approaches before detailed design work begins.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit It helps explore product or technical concepts, compare proposed approaches, refine one with the user, and save the resulting design.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/raine/consult-llm/review
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 raine/consult-llm --skill review
Clone the repo
git clone --depth 1 https://github.com/raine/consult-llm

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 review

README.md
[![agentmods](https://agentmods.dev/badge/skills/raine/consult-llm/review.svg)](https://agentmods.dev/skills/raine/consult-llm/review)
Your own site
<a href="https://agentmods.dev/skills/raine/consult-llm/review"><img src="https://agentmods.dev/badge/skills/raine/consult-llm/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,275 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Data Exfiltration · line 102
    Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.
    Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
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 $0.00040 $0.02275
Opus 5 $0.00020 $0.01137
Sonnet 5 $0.00008 $0.00455
Haiku 4.5 $0.00004 $0.00228

Measured 8d ago against content hash b0b718f9875b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

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 8d 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/review/SKILL.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Collect critical, honest feedback from all LLMs on an artifact. Push back on weak arguments. Report both consensus findings and unresolved disagreements.

Phase 0: Load consult-llm skill

Load the consult-llm skill before proceeding — it defines the invocation contract (stdin heredoc, flags, output format, multi-turn). Do not call the CLI without loading it first.

Arguments: $ARGUMENTS

Check the arguments for flags:

Mode flags:

  • --rounds N → number of critique rounds (default: 2, max: 3)
  • --dry-run → skip the final synthesis, just show raw reviews
  • --models <list> → comma-separated selectors/model IDs to use as reviewers (default: gemini,openai,anthropic,deepseek)

Strip all flags from arguments to get the review target — a file path, directory, or topic description.

Set variables:

  • REVIEWERS: list of model selectors from --models flag, or ["gemini", "openai", "anthropic", "deepseek"] if omitted
  • Build the -m flags by repeating -m <selector> for each reviewer

Available Reviewers

Discover which selectors and models are available in this environment:

!`consult-llm models`

Default reviewers (used when no --models flag is given): gemini, openai, anthropic, deepseek — all four selectors that have a configured backend.

Override with --models flag: --models gemini,openai to review with only two, or --models gemini,openai,anthropic for three. Any selector or exact model ID from the list above is accepted.

Critical Rule: No Sycophancy

This skill exists to find problems, not to validate. Instruct every LLM call with:

  • Be critical. The goal is to find weaknesses, gaps, and risks — not to praise.
  • Disagree openly. If something looks wrong, say so directly. Do not soften criticism to be polite.
  • Push back. If another reviewer dismissed a concern too easily, challenge them.
  • Unresolved disagreements are fine. Not everything needs consensus. Flag genuine disagreements clearly rather than papering over them.

Read the full file on GitHub · 221 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. 8d ago First seen · 221 lines · 40 tokens per session scan A b0b718f9875b

Subscribe to this mod's changes

review is a skill published in the GitHub repository raine/consult-llm (132 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 2,275 once invoked, about $0.0002 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens