adobe-cja-mcp: Instructions file for Claude Code

CLAUDE.md

adobe-cja-mcp CLAUDE.md is an instructions file for Claude Code from markhilton/adobe-cja-mcp. It costs 1,908 tokens per session, scanned A, original, MIT.

Repository-specific instructions for Claude Code when working on an Adobe Customer Journey Analytics server project written in Python.

In plain words
What is it for?
They guide code changes, tests, documentation, and repository navigation while working on this analytics server.
Why use it?
They keep files in the expected folders and prevent temporary reports, tests, or source files from cluttering the project root.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is markhilton/adobe-cja-mcp's own configuration. It tells Claude Code how to work on adobe-cja-mcp 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 adobe-cja-mcp configures โ†’

Reuse

Borrowing it

Nothing to install: this file belongs to markhilton/adobe-cja-mcp. 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/markhilton/adobe-cja-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/markhilton/adobe-cja-mcp

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 adobe-cja-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/markhilton/adobe-cja-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/markhilton/adobe-cja-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/markhilton/adobe-cja-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/markhilton/adobe-cja-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80ร—15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80ร—15 button for adobe-cja-mcp CLAUDE.md

Your own site ยท 80ร—15
<a href="https://agentmods.dev/instructions/markhilton/adobe-cja-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/markhilton/adobe-cja-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,908 This file is loaded in full into every session.
When invoked 1,908 The same file โ€” it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file โ€” 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 $0.01908 $0.01908
Opus 5.5 $0.00763 $0.00763
Sonnet 5.5 $0.00382 $0.00382
Haiku 4.5 $0.00191 $0.00191

Measured 2mo ago against content hash 3f9147ba95c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

adobe-cja-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories โ€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ€” 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 ยท 218 lines

How it starts

The opening of the file, as written. The whole thing โ€” 218 lines โ€” 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.

๐Ÿšจ CRITICAL PROJECT RULES

File Organization

NEVER create files in the project root directory unless explicitly requested.

  • โœ… Temporary/test files โ†’ tmp/ directory (already in .gitignore)
  • โœ… Documentation โ†’ Only core docs in root: README.md, DEVELOPMENT.md, CLAUDE.md
  • โœ… Test files โ†’ tests/ directory with appropriate subdirectories
  • โœ… Source code โ†’ src/adobe_cja_mcp/ with proper module structure
  • โŒ DO NOT create random .md, .json, .txt, or report files in root
  • โŒ DO NOT create docs/ folder - use tmp/ for temporary documentation

Examples of correct file placement:

  • Test reports: tmp/api_permissions_report.json
  • Test scripts: tmp/test_something.py
  • Scratch work: tmp/scratch.txt

The tmp/ directory is excluded from git and should be used for ALL temporary artifacts.

Repository Overview

This is an Adobe Customer Journey Analytics (CJA) MCP server project - a Python-based Model Context Protocol server that exposes CJA analytics capabilities through FastMCP.

Project Structure

adobe-cja-mcp/
โ”œโ”€โ”€ src/adobe_cja_mcp/     # Main source code
โ”‚   โ”œโ”€โ”€ auth/              # OAuth authentication
โ”‚   โ”œโ”€โ”€ client/            # CJA API client
โ”‚   โ”œโ”€โ”€ models/            # Pydantic schemas
โ”‚   โ”œโ”€โ”€ tools/             # MCP tool implementations
โ”‚   โ”œโ”€โ”€ utils/             # Configuration and utilities
โ”‚   โ””โ”€โ”€ server.py          # Main MCP server entry point
โ”œโ”€โ”€ tests/                 # Test suite
โ”‚   โ””โ”€โ”€ integration/       # Integration tests
โ”œโ”€โ”€ tmp/                   # Temporary files (gitignored)
โ”œโ”€โ”€ README.md              # Project documentation
โ”œโ”€โ”€ DEVELOPMENT.md         # Development progress tracker
โ””โ”€โ”€ CLAUDE.md             # This file

Adobe CJA MCP Server (Python/FastMCP)

Build and Run Commands

# Install dependencies with uv
uv sync

# Run tests
uv run pytest tests/integration/ -v

# Run with coverage
uv run pytest tests/integration/ --cov=src/adobe_cja_mcp

# Run the MCP server (via Claude Desktop)
# See Claude Desktop config at: ~/Library/Application Support/Claude/claude_desktop_config.json

Read the full file on GitHub ยท 218 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. 2mo ago First seen ยท 218 lines ยท 1,908 tokens per session scan A 3f9147ba95c0

Subscribe to this mod's changes

adobe-cja-mcp CLAUDE.md is an instructions file published in the GitHub repository markhilton/adobe-cja-mcp (0 stars, last pushed 10mo ago), licensed MIT. It adds 1,908 tokens to every session, about $0.0076 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.

Related

adobe-cja-mcp CLAUDE.md compared with instructions from other repositories

adobe-cja-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
adobe-cja-mcp CLAUDE.mdmarkhilton/adobe-cja-mcpInstructions file010mo agoMITA1,908Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot