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 skills/nutdnuy/quantcoder-plugin/quantcoder-researchnpx skills add nutdnuy/quantcoder-plugin --skill quantcoder-researchgit 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 | $0.00105 | $0.00851 |
| Opus 5 | $0.00053 | $0.00426 |
| Sonnet 5 | $0.00021 | $0.00170 |
| Haiku 4.5 | $0.00011 | $0.00085 |
Grade A, and why
quantcoder-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QuantCoder Research
QuantCoder plugin is an agent-native research workflow for turning quantitative papers into draft QuantConnect LEAN algorithms. Claude Code or Codex Agent does the summarization, reasoning, and code drafting; QuantCoder utilities provide paper search/download, local QC linting, and optional QuantConnect validation/backtesting. Treat it as a research scaffold, not a source of guaranteed trading performance.
Preconditions
- Python 3.10+.
- Install the package from this plugin root when CLI utilities are needed:
cd "${CLAUDE_PLUGIN_ROOT:-.}"
uv run quantcoder --help
-
Claude Code or Codex is the LLM layer. Do not require a separate local model server for the default plugin workflow.
-
QuantConnect validation/backtesting needs environment variables or
~/.quantcoder/.env:
QUANTCONNECT_API_KEY=...
QUANTCONNECT_USER_ID=...
- Optional deep search and publishing:
TAVILY_API_KEY,NOTION_API_KEY,NOTION_DATABASE_ID.
Core Workflow
- Search for papers:
quantcoder search "momentum trading" --num 5
quantcoder search "mean reversion" --deep --num 10
- Download source material:
quantcoder download 1
- Summarize with the active agent:
- Read the PDF/text or user-provided paper summary.
- Extract: strategy hypothesis, asset universe, signal formula, rebalance rule, risk controls, data needs, lookback windows, portfolio construction, and expected failure modes.
- Separate facts from assumptions and interpretations.
- Generate a QuantConnect draft with the active agent:
- Write LEAN Python code directly in the workspace.
- Prefer simple, auditable implementation over clever abstraction.
- Add only comments that clarify non-obvious paper-to-code translation choices.
- Verify before interpreting results:
quantcoder validate generated_code/algorithm_1.py --local-only
quantcoder validate generated_code/algorithm_1.py
quantcoder backtest generated_code/algorithm_1.py --start 2020-01-01 --end 2024-01-01
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 · 107 lines · 105 tokens per session scan A 336ffbde4953
quantcoder-research is a skill published in the GitHub repository nutdnuy/quantcoder-plugin (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 105 tokens to every session and 851 once invoked, about $0.0005 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 skills, from other repositories
brain-paper-to-alpha-plugin
Use for WorldQuant BRAIN alpha research, paper-to-alpha workflows, BrainAlpha M0-M5 candidate generation, BRAIN expression triage, failed-alpha repair, simulation handoff, low-correlation pool review, or when the user mentions Papertocode, WorldQuant BRAIN, Brain alpha mining, IQC, alpha examples, alpha mutation…
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…
copilotkit-develop
Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.
adr-hshare
ADR/H-share/A-share cross-listing premium analysis — track pricing gaps between US-listed ADRs, HK-listed H-shares, and A-shares for arbitrage signals, dual-listing valuation, and delisting risk assessment.
bottleneck-hunter
Supply-chain bottleneck arbitrage. Given a super-trend (AI infra, energy transition, defense, semiconductor reshoring, space economy), decompose its physical supply chain down to Layer 2/3 choke points (optics, lasers, InP/SOI substrates, IC substrates, probe cards, specialty fiberglass...) and surface under-the-radar…