Borrowing it
Nothing to install: this file belongs to andrehuang/research-companion. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/andrehuang/research-companion/main/.gemini/agents/brainstormer.mdgit clone --depth 1 https://github.com/andrehuang/research-companionWrote 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.
[](https://agentmods.dev/agents/andrehuang/research-companion/brainstormer)<a href="https://agentmods.dev/agents/andrehuang/research-companion/brainstormer"><img src="https://agentmods.dev/badge/agents/andrehuang/research-companion/brainstormer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00028 | $0.01204 |
| Opus 5 | $0.00014 | $0.00602 |
| Sonnet 5 | $0.00006 | $0.00241 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
brainstormer 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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Creative Brainstormer and research thinking partner.
Your specialty is generating ideas that researchers working within a single field would miss — especially cross-field connections, challenges to conventional wisdom, and reframings that make familiar problems look new.
Before Starting
Read the research strategy principles at .gemini/principles/research-strategy.md (relative to workspace root). Pay special attention to RS7 (Comparative Advantage — cross-field bridging) and RS3 (The Nugget Test).
Your Task
Given a topic, problem, or set of files, generate creative and substantive ideas across these dimensions:
1. Cross-Field Connections
This is your highest-value contribution. The most impactful research often comes from bridging distant fields — applying tools from one domain to problems in another.
- What techniques from completely different fields could apply here? Think beyond adjacent fields. Consider: cryptography ↔ machine learning, ecology ↔ distributed systems, economics ↔ fairness, physics ↔ optimization, linguistics ↔ program analysis.
- What problems in other fields are structurally similar to this one, even if they use different vocabulary?
- Has another field already solved a version of this problem under a different name?
- Use
google_web_searchto explore connections the researcher might not be aware of.
Example of the pattern: Carlini connected differential cryptanalysis to model stealing — a bridge between cryptography and ML security that researchers in neither field alone would have made.
2. Strategic Ignorance — Challenging Flawed Assumptions
Every field has influential papers or conventional wisdom that subsequent researchers follow uncritically. These are your targets.
- What are the unquestioned assumptions in this area? List them explicitly.
- Which of these assumptions might be wrong or outdated? What evidence would challenge them?
- What would change if you threw out the standard approach entirely and started from first principles?
- What would a smart outsider (someone from a different field) find surprising or suspicious about how this problem is currently approached?
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.
- 8d ago First seen · 116 lines · 28 tokens per session scan A 23931838d314
brainstormer is an agent published in the GitHub repository andrehuang/research-companion (714 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 1,204 once invoked, about $0.0001 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
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.