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.
npx agentmods add commands/nutdnuy/brain-paper-to-alpha-plugin/brain-setupgit clone --depth 1 https://github.com/nutdnuy/brain-paper-to-alpha-pluginWrote 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/commands/nutdnuy/brain-paper-to-alpha-plugin/brain-setup)<a href="https://agentmods.dev/commands/nutdnuy/brain-paper-to-alpha-plugin/brain-setup"><img src="https://agentmods.dev/badge/commands/nutdnuy/brain-paper-to-alpha-plugin/brain-setup.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 | $0.00009 | $0.00150 |
| Opus 5 | $0.00005 | $0.00075 |
| Sonnet 5 | $0.00002 | $0.00030 |
| Haiku 4.5 | $0.00001 | $0.00015 |
Grade A, and why
brain-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Check the plugin-local artifact helper.
Run:
cd "${CLAUDE_PLUGIN_ROOT:-$PWD}" && python3 scripts/wq_brain_alpha.py --help
cd "${CLAUDE_PLUGIN_ROOT:-$PWD}" && python3 -c "from scripts import wq_brain_alpha; print('brain artifact helper ok')"
Report whether the CLI and tests are available. Also remind the user that this plugin does not store credentials and does not run live WorldQuant BRAIN simulations unless explicitly requested in a trusted workspace.
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.
- 4d ago First seen · 19 lines · 9 tokens per session scan A 1f06e1785efc
brain-setup is a command published in the GitHub repository nutdnuy/brain-paper-to-alpha-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 150 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
quantcoder-generate
Generate a QuantConnect LEAN draft with Claude Code or Codex Agent.
quantcoder-backtest
Run a QuantConnect backtest for a generated algorithm.
quantcoder-setup
Check local QuantCoder plugin utilities and optional QuantConnect setup.
quantcoder-validate
Lint or compile-check a QuantConnect Python algorithm through QuantCoder.
quantcoder-search
Search for quantitative research papers with QuantCoder.
cli-anything-web:validate
Validate a cli-anything-web CLI against the tiered quality checklist (Tier 1 critical / Tier 2 comprehensive). Reports per-category and per-tier results.