Borrowing it
Nothing to install: this file belongs to HimanshuMohanty-Git24/RakshaQuant. 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/HimanshuMohanty-Git24/RakshaQuant/main/CLAUDE.mdgit clone --depth 1 https://github.com/HimanshuMohanty-Git24/RakshaQuantWrote 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/himanshumohanty-git24/rakshaquant/claude-md)<a href="https://agentmods.dev/instructions/himanshumohanty-git24/rakshaquant/claude-md"><img src="https://agentmods.dev/badge/instructions/himanshumohanty-git24/rakshaquant/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/himanshumohanty-git24/rakshaquant/claude-md"><img src="https://agentmods.dev/badge/instructions/himanshumohanty-git24/rakshaquant/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 | $0.02881 | $0.02881 |
| Opus 5.5 | $0.01152 | $0.01152 |
| Sonnet 5.5 | $0.00576 | $0.00576 |
| Haiku 4.5 | $0.00288 | $0.00288 |
Grade A, and why
RakshaQuant 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 1mo 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project
RakshaQuant (Platform v2) is a paper-trading platform for NSE cash equities, built for a controlled experiment. A deterministic engine trades three paired books on the same signals: A has no advisor, B has a local typed decision model (Laya, escalating to Jev) as a veto, and C has an LLM as a veto. The question is whether AI adds value net of its cost.
- Everything is recorded in an SQLite event store.
- There is no broker order path: every order fills on a simulated broker.
- Read docs/architecture.md first.
- The build plan is docs/plan/2026-10-01-platform-v2-plan.md, the source of truth. Its status, decisions log (OD-n) and open owner questions (OQ-n) are in docs/plan/PROGRESS.md.
Hard rules:
-
Never add a live-broker path or enable real orders. Paper only, unless the owner explicitly asks.
-
Never print, log or echo values from
.env: it holds real credentials. Read settings in code viaget_settings(); secrets areSecretStr. Run tools withRAKSHAQUANT_ENV_FILE=nonewhen they don't need the real configuration. -
No pushing, PRs or paid API calls in loops without the owner's go-ahead.
-
During the month run, the trading path is frozen except for P0 fixes:
src/strategies,src/risk,src/oms,src/brokers/simulatedandsrc/decision;src/config/experiment.yamland theRISK_*limits.
Commands
Dependencies are managed with uv. The import package is
src (from src.<module> import ...). Extras:
dev: pytest, ruff, mypy, hypothesis, pytest-benchmark;web: FastAPI, uvicorn;decision-local: Laya, which pulls torch;broker-dhan: the DhanHQ SDK, unused by the engine.
uv sync --extra dev --extra web # add --extra decision-local for Laya
uv run python scripts/check_config.py # readiness check (exit 2 on a bad config)
uv run python scripts/run_live_trading.py # today's paper session, Rich terminal dashboard
uv run python scripts/run_live_trading.py --mode web # same session, browser console
uv run python scripts/run_live_trading.py --demo [--mode web] # bundled synthetic day, var/demo/
uv run python scripts/replay_day.py --date YYYY-MM-DD # re-run a recorded day
uv run python scripts/daily_report.py --date YYYY-MM-DD # regenerate a day's report
uv run python scripts/validate_strategy.py --start ... --end ... # backtest + edge gate
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.
- 1mo ago Changed · -27 lines · -1,284 tokens per session 5e9455258eb7
- 2mo ago First seen · 243 lines · 4,165 tokens per session scan A 95770d2cfaed
RakshaQuant CLAUDE.md is an instructions file published in the GitHub repository HimanshuMohanty-Git24/RakshaQuant (72 stars, last pushed 2d ago), licensed MIT. It adds 2,881 tokens to every session, about $0.0115 per session on Opus 5.5. 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 2026-08-30.
RakshaQuant CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| RakshaQuant CLAUDE.mdHimanshuMohanty-Git24/RakshaQuant | Instructions file | 72 | 2d ago | MIT | A | 2,881 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |