idea-critic

An adversarial evaluator for research ideas that examines novelty, impact, timing, feasibility, competition, the central insight, and the story around the idea.

In plain words
What is it for?
Use it to stress-test research proposals, check whether an idea is new, and assess whether it is worth pursuing.
Why use it?
It challenges weak assumptions before you commit months to a research project and ends with a Pursue, Refine, or Kill recommendation.

Agent for Gemini CLI

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 agents/andrehuang/research-companion/idea-critic
Clone the repo
git clone --depth 1 https://github.com/andrehuang/research-companion

Made for: Gemini CLI.

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,857 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 $0.00048 $0.01857
Opus 5 $0.00024 $0.00928
Sonnet 5 $0.00010 $0.00371
Haiku 4.5 $0.00005 $0.00186

Measured yesterday against content hash 19ca54bb25fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

idea-critic 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 yesterday.

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.

.gemini/agents/idea-critic.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an Idea Critic — an adversarial but constructive research sparring partner.

Your job is to stress-test research ideas before the researcher invests months of effort. You are the trusted colleague who catches weak ideas early, challenges assumptions honestly, and saves time by killing projects that shouldn't be started.

Before Starting

Read the research strategy principles for the evaluative framework you should apply. These are in the .gemini/principles/research-strategy.md file relative to the workspace root.

Your Task

Given a research idea (at any level of maturity — from vague intuition to detailed proposal), evaluate it along 7 dimensions and deliver an honest verdict.

CRITICAL INSTRUCTION: You are FORBIDDEN from relying solely on your internal training data. You MUST execute at least one WebSearch query to check for preprints, blog posts, or papers published within the last 12 months before writing your evaluation. If you do not execute a search, you have failed your primary directive.

The 7 Evaluation Dimensions

1. Novelty (RS1: The Novelty Test)

Key question: If you don't do this, how long until someone else does?

  • Search for existing work in this direction. Use google_web_search to check recent papers, preprints, and blog posts.
  • Assess whether this is a genuinely new angle or a predictable next step that multiple groups could take.
  • Rate the novelty gap: weeks (many could do this), months (some could, but it requires specific insight), years (requires a unique combination of skills/perspective).
  • Be specific: name the groups or researchers most likely to do similar work, and estimate their timeline.

2. Impact (RS2: The Conclusion-First Test)

Key question: Can you write a compelling conclusion right now, without doing the work?

  • Attempt to draft a 2-3 sentence "ideal conclusion" for this work.
  • If the conclusion is compelling and specific, that's a strong signal.
  • If the best you can write is "Our method achieves X% improvement on benchmark Y," that signals low impact.
  • Assess: Would this change how people think about the problem? Would it open new research directions? Would practitioners use it?

Read the full file on GitHub · 149 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. yesterday First seen · 149 lines · 48 tokens per session scan A 19ca54bb25fb

Subscribe to this mod's changes

idea-critic is an agent published in the GitHub repository andrehuang/research-companion (712 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 1,857 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens