Borrowing it
Nothing to install: this file belongs to bayesimpact/bayes-platform. 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/bayesimpact/bayes-platform/main/CLAUDE.mdgit clone --depth 1 https://github.com/bayesimpact/bayes-platformWrote 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/bayesimpact/bayes-platform/claude-md)<a href="https://agentmods.dev/instructions/bayesimpact/bayes-platform/claude-md"><img src="https://agentmods.dev/badge/instructions/bayesimpact/bayes-platform/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/bayesimpact/bayes-platform/claude-md"><img src="https://agentmods.dev/badge/instructions/bayesimpact/bayes-platform/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 | $0.02532 | $0.02532 |
| Opus 5.5 | $0.01013 | $0.01013 |
| Sonnet 5.5 | $0.00506 | $0.00506 |
| Haiku 4.5 | $0.00253 | $0.00253 |
Grade A, and why
bayes-platform 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 6d 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 — 154 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 Structure
This is a Turborepo monorepo with the following structure:
apps/api- NestJS backend application (runs on port 3000)apps/pdf-converter- Go service rendering PDFs to PNG page images in the platform bucket (S3-compatible) for image-only LLMs (Gemma, MedGemma), runs on port 3002 and serves the PDF export MCP endpoint at/mcp;npm run devstarts it when Go is installed andapps/pdf-converter/.envexistsapps/desk- The Desk, rebuilt on the frontend stack of ADR 0031 (Vite, TanStack Router and Query, shadcn on Base UI, Lingui), runs on port 5177 at/app/; seeapps/desk/AGENTS.mdapps/web- Vite + React frontend application (runs on port 5173)packages/@caseai-connect/api-contracts- Shared API contracts and DTOspackages/@caseai-connect/desk-contracts- The Desk's view of the API: the routes it calls and the Zod schemas of their responses, whichapps/deskchecks at runtimepackages/@repo/typescript-config- Shared TypeScript configurationspackages/@caseai-connect/ui- Shared React component library
Development Commands
All commands should be run from the root directory using Turbo (via npm scripts):
Development
npx turbo dev- Start all applications in development modenpx turbo dev --filter=api- Start only the API applicationnpx turbo dev --filter=web- Start only the web application
Building
npx turbo build- Build all applications and packagesnpx turbo build --filter=api- Build only the API applicationnpx turbo build --filter=web- Build only the web application
Testing
npx turbo test- Run all testsnpx turbo test --filter=api- Run API tests onlynpx turbo test --filter=web- Run web tests only
Code Quality
npx turbo lint- Lint all packages and applications
TypeScript Compilation Check
cd apps/api && npx tsc --noEmit- Check API TypeScript without emitting filescd apps/web && npx tsc --noEmit- Check web TypeScript without emitting files
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.
- 6d ago Changed · +8 lines · +251 tokens per session 59776561adbb
- 8d ago Changed · -3 tokens per session 684ea31686c5
- 9d ago Changed · +9 tokens per session 94820beb12e0
- 14d ago Changed · +4 lines · +62 tokens per session 6acbbd18a11a
- 15d ago Changed · +3 lines · +172 tokens per session de58101b56c7
- 22d ago Changed · +3 tokens per session 115c2932c5e1
- 25d ago Changed · +3 lines · +191 tokens per session 0ed490688de5
- 28d ago Changed · +1 lines · +67 tokens per session a83ff247ed3d
- 1mo ago Changed · +7 lines · +240 tokens per session 8d49b550e603
- 1mo ago First seen · 128 lines · 1,540 tokens per session scan A eadb4b6c64c6
bayes-platform CLAUDE.md is an instructions file published in the GitHub repository bayesimpact/bayes-platform (23 stars, last pushed yesterday), licensed MIT. It adds 2,532 tokens to every session, about $0.0101 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 2026-09-14.
bayes-platform CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bayes-platform CLAUDE.mdbayesimpact/bayes-platform | Instructions file | 23 | yesterday | MIT | A | 2,532 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |