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 instructions/kars0311/quantforge/agents-mdgit clone --depth 1 https://github.com/kars0311/quantforgeWhat 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 | $0.01180 | $0.01180 |
| Opus 5 | $0.00590 | $0.00590 |
| Sonnet 5 | $0.00236 | $0.00236 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
quantforge AGENTS.md 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — build guide for this repo
You (an AI coding agent) are building out this project from a scaffold. This file is the operating
manual. Read docs/PROJECT_BRIEF.md, docs/architecture.md, and docs/TEN_WEEK_PLAN.md before
starting.
What this is
An open-source, AI-driven, polyglot quant research pipeline: data → strategies → backtest → portfolio optimization → risk/perf analytics → interactive UI → cloud, with an AI research agent and a natural-language interface driving the pipeline over MCP tools.
Non-negotiable rules
- Statistical rigor (this is the whole point):
- No look-ahead bias. A position decided using data through day t earns day t+1's return.
The engine enforces this with
positions.shift(1). Never let a signal peek at same-day data it couldn't have known at decision time. - Transaction costs modeled on turnover.
- Survivorship bias acknowledged (fixed historical universe; document the caveat).
- Out-of-sample: the AI agent gets train/validation only; the holdout is scored once and never optimized against. An LLM iterating on the test set is p-hacking — prevent it.
- Prove correctness: validate the custom engine against
backtesting.py(tests/test_engine_vs_backtestingpy.py).
- No look-ahead bias. A position decided using data through day t earns day t+1's return.
The engine enforces this with
- Safety / cost (a public URL with paid AI hooks is a liability):
- All Claude API calls go through
ai/budget.py(hardAI_BUDGET_USD_*caps + kill-switch). PUBLIC_MODE=on⇒ parameter-only: never execute LLM-generated code on the server; only vetted strategies + whitelisted params. Gate live AI behindDEMO_PASSCODE; rate-limit.
- All Claude API calls go through
- Architecture discipline:
- Everything depends on the
Strategy/Engineinterfaces inengine/base.py. Freeze them. - Cross-stage / cross-language hand-offs use the Arrow/Parquet contract in
interchange.py. metrics/performance.pyis the single source of truth for metrics; the R layer must match it.
- Everything depends on the
- Defensibility: add docstrings that explain why, not just what. The human author must be able to explain every component in an interview. Prefer clear, conventional code over cleverness.
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 · 89 lines · 1,180 tokens per session scan A a577b9a783dc
quantforge AGENTS.md is an instructions file published in the GitHub repository kars0311/quantforge (0 stars, last pushed 2d ago), licensed MIT. It adds 1,180 tokens to every session, about $0.0059 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.