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/quantcoder-plugin/quantcoder-generategit clone --depth 1 https://github.com/nutdnuy/quantcoder-pluginWhat 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 | $0.00014 | $0.00205 |
| Opus 5 | $0.00007 | $0.00102 |
| Sonnet 5 | $0.00003 | $0.00041 |
| Haiku 4.5 | $0.00001 | $0.00020 |
Grade A, and why
quantcoder-generate 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.
What it actually says
Generate QuantConnect code with the active Claude Code / Codex agent.
Use $ARGUMENTS as the source paper/summary path and optional output path.
Agent workflow:
- Read the paper or summary.
- Extract the strategy hypothesis, universe, signal formula, rebalance cadence, risk controls, data assumptions, and paper equations.
- Write a QuantConnect LEAN Python draft directly.
- Run local validation/linting with:
cd "${CLAUDE_PLUGIN_ROOT}" && uv run quantcoder validate <output_path> --local-only
- Summarize the strategy logic and flag paper-to-code assumptions, possible data leakage, transaction-cost omissions, and math-fidelity risks.
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.
- yesterday First seen · 25 lines · 14 tokens per session scan A f41167a0c57d
quantcoder-generate is a command published in the GitHub repository nutdnuy/quantcoder-plugin (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 205 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 2026-08-31.
Other commands, from other repositories
brain-generate-candidates
Generate a small, source-grounded BRAIN alpha candidate batch.
brain-init-run
Create a local BRAIN paper-to-alpha research run folder.
brain-setup
Check local WQ BRAIN alpha artifact utilities.
brain-validate-run
Validate a local BRAIN alpha research run folder.
brain-intake
Convert a paper, report, idea, alpha expression, or BRAIN result into a research card.
brain-repair
Diagnose failed BRAIN alpha results and propose a repair batch.