Dex: Instructions file for Claude Code

CLAUDE.md

Dex CLAUDE.md is an instructions file for Claude Code from davekilleen/Dex. It costs 9,361 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for Dex, a personal knowledge system. The instructions cover setup, user profiles, reference material, and extensions.

In plain words
What is it for?
Use it when setting up or changing Dex through Claude Code, including its documentation and user extensions.
Why use it?
It gives Claude Code the project-specific context and rules needed to work on Dex consistently.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is davekilleen/Dex's own configuration. It tells Claude Code how to work on Dex itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Dex configures →

Reuse

Borrowing it

Nothing to install: this file belongs to davekilleen/Dex. 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/davekilleen/Dex/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/davekilleen/Dex

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.

agentmods badge for Dex CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/davekilleen/dex/claude-md/github.svg)](https://agentmods.dev/instructions/davekilleen/dex/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/davekilleen/dex/claude-md"><img src="https://agentmods.dev/badge/instructions/davekilleen/dex/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.

agentmods 80×15 button for Dex CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/davekilleen/dex/claude-md"><img src="https://agentmods.dev/badge/instructions/davekilleen/dex/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9,361 This file is loaded in full into every session.
When invoked 9,361 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.09361 $0.09361
Opus 5.5 $0.03744 $0.03744
Sonnet 5.5 $0.01872 $0.01872
Haiku 4.5 $0.00936 $0.00936

Measured 28d ago against content hash 72fa1a7bf451, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Dex 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 28d 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 · 729 lines

How it starts

The opening of the file, as written. The whole thing — 729 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dex - Your Personal Knowledge System

You are Dex, a personal knowledge assistant. You help the user organize their professional life - meetings, projects, people, ideas, and tasks. You're friendly, direct, and focused on making their day-to-day easier.


First-Time Setup

If System/.onboarding-complete doesn't exist, this is a fresh setup.

Process:

  1. Call start_onboarding_session() from onboarding-mcp to initialize or resume
  2. Read .claude/flows/onboarding.md for the conversation flow
  3. Use MCP validate_and_save_step() after each step to enforce validation
  4. CRITICAL: Step 4 (email_domain) is MANDATORY and validated by the MCP
  5. Before finalization, call get_onboarding_status() to verify completion
  6. Call verify_dependencies() to check Python packages and Calendar.app
  7. Call finalize_onboarding() to create vault structure and configs

Why MCP-based:

  • Bulletproof validation - cannot skip Step 4 (email_domain) or other required fields
  • Session state enables resume if interrupted
  • Automatic MCP configuration with VAULT_PATH substitution
  • Structured error messages with actionable guidance

Phase 2 - Getting Started:

After core onboarding (Step 9), offer Phase 2 tour via /getting-started skill:

  • Adaptive based on available data (calendar, Granola, or neither)
  • With data: Analyzes what's there, offers to process meetings/create pages
  • Without data: Guides tool integration, builds custom MCPs
  • Always: Low pressure, clear escapes, educational even when things don't work

The system automatically suggests /getting-started at next session if vault < 7 days old.


User Profile

Name: Not yet configured Role: Not yet configured Company Size: Not yet configured Working Style: Not yet configured Pillars:

  • Not yet configured

Read the full file on GitHub · 729 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.

  1. 28d ago Changed · +18 lines · +212 tokens per session 72fa1a7bf451
  2. 1mo ago Changed · +3 lines · +117 tokens per session d57a74f38c8b
  3. 1mo ago Changed · +15 lines · +321 tokens per session 47b9c682b794
  4. 1mo ago First seen · 693 lines · 8,711 tokens per session scan A 88d09154ac4c

Subscribe to this mod's changes

Dex CLAUDE.md is an instructions file published in the GitHub repository davekilleen/Dex (508 stars, last pushed 3d ago), licensed MIT. It adds 9,361 tokens to every session, about $0.0374 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 2026-09-03.

Related

Other instructions, from other repositories

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 · 9,715 tokens

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 · 7,581 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens