What is context-driven-documentation CLAUDE.md?

Project instructions for keeping structured documentation about a software project's purpose, architecture, design, commands, and framework setup.

They help teams document project rules, architecture, development commands, and the current context used by AI-assisted development.

They give an AI coding assistant shared project context, reducing the need to explain the same background in every conversation.

How guilhermegouw/context-driven-documentation configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to guilhermegouw/context-driven-documentation. 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/guilhermegouw/context-driven-documentation/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/guilhermegouw/context-driven-documentation

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/guilhermegouw/context-driven-documentation/claude-md/github.svg)](https://agentmods.dev/instructions/guilhermegouw/context-driven-documentation/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/guilhermegouw/context-driven-documentation/claude-md"><img src="https://agentmods.dev/badge/instructions/guilhermegouw/context-driven-documentation/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/guilhermegouw/context-driven-documentation/claude-md"><img src="https://agentmods.dev/badge/instructions/guilhermegouw/context-driven-documentation/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,378 This file is loaded in full into every session.

When invoked 3,378 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	$0.03378	$0.03378
Opus 5.5	$0.01351	$0.01351
Sonnet 5.5	$0.00676	$0.00676
Haiku 4.5	$0.00338	$0.00338

Measured 2mo ago against content hash 835aaac09d16, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

context-driven-documentation 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 2mo 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 · 386 lines

How it starts

The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Constitution

This file serves as the foundational context for all AI-assisted development in this project. Complete this constitution to enable powerful, context-aware AI collaboration.

Project Overview

Project: Context-Driven Documentation (CDD Framework)

Purpose: A complete engineering intelligence system that makes human-AI collaboration feel natural, powerful, and productive.

Target Users: Software engineers and development teams working with AI assistants

Business Domain: Software engineering tools and AI-assisted development

Core Value Proposition: Eliminates the need to repeatedly provide context to AI assistants. Capture your project's context once in structured documentation, and AI assistants immediately understand your project, architecture, and current work - making every conversation start from shared understanding instead of zero.

AI-First Development Philosophy:

MVP Focus: Claude Code as primary interface - AI-assisted engineering is the core workflow
Future Vision: Support for additional AI clients while maintaining AI-first approach
Philosophy: Building for a new paradigm of software development where AI collaboration is fundamental, not supplementary

Architecture & Design Patterns

Architecture Philosophy: AI-First Design - use well-known, conventional patterns that AI assistants can recognize and understand immediately. Favor clarity and familiarity over cleverness.

Core Architectural Patterns:

Handler Pattern: Separate handlers for different file types (ConstitutionHandler, TicketSpecHandler, etc.) - each knows how to work with its specific file format
Command Pattern: CLI commands via Click for tooling operations
- cdd init - Framework initialization (options: --force, --minimal)
- cdd new - Ticket and documentation creation with 6 variants:
  - Tickets: feature, bug, spike, enhancement
  - Documentation: guide, feature
Slash Commands: AI-driven commands (/socrates, /plan) that turn Claude into specialized personas for intelligent conversations
- /socrates - Interactive requirements gathering through natural conversation
- /plan - Autonomous implementation planning with minimal questions
Template-Driven: Use templates to define structure, AI reads templates to understand what needs to be captured

Read the full file on GitHub · 386 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.

2mo ago First seen · 386 lines · 3,378 tokens per session scan A 835aaac09d16

Subscribe to this mod's changes

context-driven-documentation CLAUDE.md is an instructions file published in the GitHub repository guilhermegouw/context-driven-documentation (5 stars, last pushed 1y ago), licensed MIT. It adds 3,378 tokens to every session, about $0.0135 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 2026-08-31.

Writing and docs

context-driven-documentation CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
context-driven-documentation CLAUDE.mdguilhermegouw/context-driven-documentation	Instructions file	5	1y ago	MIT	A	3,378	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
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
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

context-driven-documentation: Instructions file for Claude Code