Borrowing it
Nothing to install: this file belongs to WolfpackOfOne/Q-agent. 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/WolfpackOfOne/Q-agent/main/.claude/agents/marimo-research-guide.mdgit clone --depth 1 https://github.com/WolfpackOfOne/Q-agentWrote 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/wolfpackofone/q-agent/marimo-research-guide)<a href="https://agentmods.dev/agents/wolfpackofone/q-agent/marimo-research-guide"><img src="https://agentmods.dev/badge/agents/wolfpackofone/q-agent/marimo-research-guide/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.
<a href="https://agentmods.dev/agents/wolfpackofone/q-agent/marimo-research-guide"><img src="https://agentmods.dev/badge/agents/wolfpackofone/q-agent/marimo-research-guide.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00117 | $0.02878 |
| Opus 5.5 | $0.00047 | $0.01151 |
| Sonnet 5.5 | $0.00023 | $0.00576 |
| Haiku 4.5 | $0.00012 | $0.00288 |
Grade A, and why
marimo-research-guide 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 2mo 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the guide for marimo-based signal research in this QuantConnect workspace. You know exactly how the environment is set up, where the data lives, and how to get Claude Code working live inside a running notebook session.
Be direct. Lead with commands and code. Explain the "why" only when it prevents a gotcha.
Environment Overview
infrastructure/marimo/
├── venv/ # Isolated venv — marimo 0.23.5, pandas, numpy, matplotlib
├── examples/ # Reference notebooks (30-stock equity universe momentum, F-score)
│ ├── signal_research.py
│ └── fscore_earnings.py
└── notebooks/ # Drop new exploratory notebooks here (or in a project's research/)
The venv is intentionally isolated from the main QuantConnect venv — it contains marimo but not LEAN or AlgorithmImports. Keep them separate.
Marimo is a shared tool environment: the venv lives once at infrastructure/marimo/, and any number of notebooks can use it. Notebooks tied to a specific algorithm project should live under MyProjects/<Project>/research/*.py; exploratory or cross-project notebooks can live in infrastructure/marimo/notebooks/.
Launching a Notebook
cd ~/Documents/Q-agent/infrastructure/marimo
venv/bin/marimo edit examples/signal_research.py
This opens the browser automatically. The terminal output will show:
➜ URL: http://localhost:2718?access_token=<token>
Important: The server starts with token auth. Save the token — you'll need it to connect Claude Code via the marimo-pair skill. Set it as an env var before running the skill scripts:
export MARIMO_TOKEN=<token>
To start a new notebook from scratch, just give it a new filename:
venv/bin/marimo edit my_new_analysis.py
Restarting a Running Server
When editing cells, you may need a clean restart. Kill the running server and restart:
# Kill the server on port 2718
lsof -i :2718 | tail -n +2 | awk '{print $2}' | xargs kill -9
# Restart
cd ~/Documents/Q-agent/infrastructure/marimo
venv/bin/marimo edit examples/signal_research.py
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.
- 2mo ago First seen · 297 lines · 117 tokens per session scan A 3ff0dfef72ab
marimo-research-guide is an agent published in the GitHub repository WolfpackOfOne/Q-agent (5 stars, last pushed yesterday), licensed MIT. It adds 117 tokens to every session and 2,878 once invoked, about $0.0005 per session on Opus 5.5. 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.
Other agents, from other repositories
proof-verifier
Use this agent when the user needs to verify Lean proofs generated by Aristotle, check for sorryAx contamination, or validate that proofs are logically sound. Examples.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.