Borrowing it
Nothing to install: this file belongs to daviddme/AIHedgeFund. 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/daviddme/AIHedgeFund/main/CLAUDE.mdgit clone --depth 1 https://github.com/daviddme/AIHedgeFundWrote 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/instructions/daviddme/aihedgefund/claude-md)<a href="https://agentmods.dev/instructions/daviddme/aihedgefund/claude-md"><img src="https://agentmods.dev/badge/instructions/daviddme/aihedgefund/claude-md/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/instructions/daviddme/aihedgefund/claude-md"><img src="https://agentmods.dev/badge/instructions/daviddme/aihedgefund/claude-md.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 | $0.05331 | $0.05331 |
| Opus 5 | $0.02665 | $0.02665 |
| Sonnet 5 | $0.01066 | $0.01066 |
| Haiku 4.5 | $0.00533 | $0.00533 |
Grade A, and why
AIHedgeFund CLAUDE.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 9d 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 — 1,096 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file is the operating guide for Claude Code and any coding agent working in this repository.
Read this file before changing code.
1. Project mission
Build ARF-OS, a multi-agent research operating system for discovering, implementing, backtesting, validating, and forward-testing systematic trading strategies.
The system is a research platform. It is not an autonomous fund, broker, or live-trading engine.
The core product promise is:
Every strategy result is reproducible, versioned, independently validated, and traceable from idea to decision.
Pine Script v6 is the canonical strategy language. A Pine-compatible local runner may be used for scale, but TradingView is the final acceptance and parity environment for Pine behaviour.
2. Read these documents
Before implementing a feature, read:
AI_RESEARCH_HEDGE_FUND_SPEC.mdLEADER_AGENT_SYSTEM_PROMPT.md- Relevant schemas in
schemas/ - Relevant ADRs in
docs/adr/ - Existing tests near the code you will change
When implementation and specification conflict, do not silently choose one. Open or update an ADR and make the conflict visible.
3. Non-negotiable architecture rules
3.1 Immutable research artefacts
Never mutate a tested strategy version.
Any change to any of the following creates a new strategy_versions row:
- Pine source
- Strategy definition
- Parameters
- Symbol
- Timeframe
- Session or timezone
- Cost model
- Position sizing
- Leverage or margin
- Execution settings
- Dataset
- Runner
- Segment assignment
Backtest and forward-test records point to the exact immutable version.
3.2 API owns state transitions
Workers do not directly change strategy lifecycle state.
Workers:
- execute a job,
- store output artefacts,
- emit a domain event or result,
- let the orchestrator/API apply transition policy.
3.3 Structured contracts are canonical
All agent outputs, handoffs, domain events, and external signal payloads must be validated with Zod.
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.
- 9d ago First seen · 1,096 lines · 5,331 tokens per session scan A 3db538b940af
AIHedgeFund CLAUDE.md is an instructions file published in the GitHub repository daviddme/AIHedgeFund (10 stars, last pushed 1mo ago), licensed MIT. It adds 5,331 tokens to every session, about $0.0267 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
vscode buildNext.instructions.md
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).
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).
langchain AGENTS.md
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.