What is decision-hub CLAUDE.md?

Project instructions for a decision-making workspace monorepo, a repository containing several related packages and a web interface. They describe its Python client and server, shared data models, React frontend, environments, and development setup.

Finding the client, server, shared, and frontend code; setting up development environments; understanding package boundaries; and changing shared data models or backend and frontend components.

They show where each part belongs and identify shared models as the single source of truth, reducing duplicated or inconsistent definitions. They also explain the technologies and environments used by the project.

How pymc-labs/decision-hub configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to pymc-labs/decision-hub. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/pymc-labs/decision-hub/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/pymc-labs/decision-hub

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/pymc-labs/decision-hub/claude-md.svg)](https://agentmods.dev/instructions/pymc-labs/decision-hub/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/pymc-labs/decision-hub/claude-md"><img src="https://agentmods.dev/badge/instructions/pymc-labs/decision-hub/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 4,910 This file is loaded in full into every session.

When invoked 4,910 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.04910	$0.04910
Opus 5	$0.02455	$0.02455
Sonnet 5	$0.00982	$0.00982
Haiku 4.5	$0.00491	$0.00491

Measured 8d ago against content hash 8a3bb3d7a4e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

decision-hub 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 8d 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.

CLAUDE.md · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Overview

Workspace Structure

This is a uv workspace monorepo with four components:

client/ — dhub-cli package (open-source CLI, published to PyPI) — import path: dhub.*
server/ — decision-hub-server package (private backend, deployed on Modal) — import path: decision_hub.*
shared/ — dhub-core package (shared domain models and SKILL.md manifest parsing) — import path: dhub_core.*
frontend/ — React + TypeScript web UI (bundled into the server at deploy time, not a uv workspace member)

shared/ is the single source of truth for data models (SkillManifest, RuntimeConfig, etc.) and manifest parsing. Both client and server depend on it — never duplicate these definitions.

Tech Stack

Backend (Python 3.11+):

FastAPI for REST API (server)
Typer + Rich for CLI (client)
Pydantic for data validation and settings
OpenRouter (Qwen) for LLM (gauntlet safety analysis, skill classification, search/ask, Cisco scanner — default backend, Gemini fallback)
Gemini for embeddings (Gemini-only, no provider switch — stored vectors and query vectors must share one embedding space, so changing the embedding model is a migration requiring a full re-embed) and as fallback chat backend
Anthropic for LLM (eval judging)
boto3 for S3 access
loguru for server logging

Frontend:

React 19 with TypeScript
Vite for bundling and dev server
React Router for routing

Important: Always use uv run to execute Python code, not python directly.

Development Setup

Environments (Dev / Prod / Local)

The project has three environments controlled by DHUB_ENV (dev | prod | local). The server defaults to dev for safety; the CLI defaults to prod for end users.

Always work against dev unless explicitly told to use prod. Prefix all CLI, server, and deploy commands with DHUB_ENV=dev:

DHUB_ENV=dev dhub list                          # CLI against dev
DHUB_ENV=dev modal deploy modal_app.py          # deploy dev Modal app (from server/)
DHUB_ENV=dev uv run --package decision-hub-server uvicorn ...  # local dev server

Read the full file on GitHub · 270 lines

Changes

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.

8d ago First seen · 270 lines · 4,910 tokens per session scan A 8a3bb3d7a4e2

Subscribe to this mod's changes

decision-hub CLAUDE.md is an instructions file published in the GitHub repository pymc-labs/decision-hub (99 stars, last pushed 26d ago), licensed MIT. It adds 4,910 tokens to every session, about $0.0246 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 2026-08-30.

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

decision-hub: Instructions file for Claude Code