Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/galliani/contextmax/claude-mdgit clone --depth 1 https://github.com/galliani/contextmaxWhat 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 | $0.01602 | $0.01602 |
| Opus 5 | $0.00801 | $0.00801 |
| Sonnet 5 | $0.00320 | $0.00320 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade A, and why
contextmax 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 2d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - AI Assistant Guidelines
This file provides comprehensive guidance to Claude Code (claude.ai/code) when working with the ContextMax codebase. It contains project-specific instructions, architectural details, and development practices that help maintain consistency and quality.
Project Overview
ContextMax is a privacy-first, browser-based web application built with Nuxt.js 3 that helps developers create precise, reusable context sets for Large Language Models (LLMs).
Core Principles
- Privacy First: All processing happens client-side, no code ever leaves the user's machine
- Developer Focused: Built by developers for developers working with complex codebases
- LLM Agnostic: Works with any LLM that accepts context (Claude, GPT, Gemini, etc.)
- Performance Optimized: Uses WebGPU, IndexedDB caching, and OPFS for speed
Development Commands
# Start development server
npm run dev
# Clean development (removes .nuxt cache)
npm run dev:clean
# Fresh start (clean + reinstall)
npm run dev:fresh
# Build for production
npm run build
# Run tests
npm run test
# Run tests with coverage
npm run test:coverage
# Generate coverage badge
npm run coverage:badge
Important Notes:
- Development server runs on port 3000
- Do not run commands to start/restart the server - assume it's already running
- Always run tests before committing changes
- Maintain 91%+ code coverage
AI Assistant Guidelines
Context Sets Tool Selection
When a user references @context:Name, resolve it via context-sets.json → sets["context:Name"].
Processing Order
- Check workflows first
- If workflows exist: Start from
workflow.start.functionand trace toend - If workflows empty: Read all files in the context, prioritizing those with
functionRefs
- File Resolution
- String → filesIndex[fileId].path → read entire file
- Object → filesIndex[fileId].path → locate specific functionRefs
- Impact Analysis
- Direct: Check context's
usesarray - Indirect: Check
filesIndex[fileId].contextsfor shared files - When modifying file_X in ContextA, also consider ContextB if both use file_X
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.
- 2d ago First seen · 224 lines · 1,602 tokens per session scan A bc17de1185e7
contextmax CLAUDE.md is an instructions file published in the GitHub repository galliani/contextmax (11 stars, last pushed 1y ago), licensed MPL-2.0. It adds 1,602 tokens to every session, about $0.0080 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.
Other instructions, from other repositories
pluribus copilot-instructions.md
Instructions for caioribeiroclw-pixel/pluribus, covering project, stack, conventions, constraints and goals.
agent-toolkit AGENTS.md
Instructions for ulises-jeremias/agent-toolkit, covering agents.md — ai agent contract, what this toolkit does, repository structure, operating rules and how to add a skill.
academic-writing-toolkit AGENTS.md
Instructions for yha9806/academic-writing-toolkit, covering academic writing project, skill discovery, project overview, directories and targets.
academic-writing-toolkit CLAUDE.md
Instructions for yha9806/academic-writing-toolkit, covering academic writing project, project overview, directories, targets and reading constraints.
ChatCrystal AGENTS.md
Instructions for ZengLiangYi/ChatCrystal, covering agents.md, project overview, commands, development (server port 3721 + client port 13721) and build for production.
core-ai AGENTS.md
Instructions for helius-labs/core-ai, covering core ai — agent instructions, repository overview, mcp server setup, api key setup and public tool surface.