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/context-hub/generator/claude-mdgit clone --depth 1 https://github.com/context-hub/generatorWhat 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 | $0.01585 | $0.01585 |
| Opus 5 | $0.00792 | $0.00792 |
| Sonnet 5 | $0.00317 | $0.00317 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade A, and why
generator 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 — 171 lines — 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.
Project Overview
This is CTX (Context Generator), a PHP 8.3+ tool for generating contextual documentation from codebases for use with LLMs. It allows developers to create structured context files from various sources including local files, Git repositories, GitHub/GitLab repos, web pages, and MCP servers.
Development Commands
Primary Commands
composer install- Install dependenciesphp ctxor./ctx- Run the context generator (main entry point)php ctx init- Initialize a new context.yaml configuration filephp ctx generate- Generate context files from configuration (alias:build,compile)php ctx server- Start the MCP server for Claude AI integrationphp ctx schema- Generate JSON schema for configuration validation
Development & Testing
composer test- Run PHPUnit testscomposer test:cc- Run tests with coverage reportcomposer cs-check- Check code style with PHP-CS-Fixer (dry run)composer cs-fix- Fix code style issuescomposer psalm- Run Psalm static analysiscomposer psalm:ci- Run Psalm with CI formattingcomposer refactor- Run Rector for automated refactoringcomposer refactor:ci- Run Rector in dry-run mode
Build Commands
The project uses Box to create PHAR executables:
- Build output goes to
.build/phar/ctx.phar - Configuration in
box.json
Architecture Overview
Core Application Structure
- Spiral Framework: Built on Spiral PHP framework using dependency injection
- Console Commands: Located in
src/Console/extendingBaseCommand - Bootloaders: Application services bootstrapped via bootloaders in
src/Application/Bootloader/ - Entry Point:
ctxscript →app.php→ Spiral application kernel
Key Components
Configuration System (src/Config/)
- YAML-based configuration with JSON schema validation
- Import system supports importing from URLs and local paths
- Environment variables supported throughout configuration
- Modular parsing with plugin system for extensibility
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 · 171 lines · 1,585 tokens per session scan A 3e47ef4198fd
generator CLAUDE.md is an instructions file published in the GitHub repository context-hub/generator (341 stars, last pushed 5mo ago), licensed MIT. It adds 1,585 tokens to every session, about $0.0079 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
ai-context-kit AGENTS.md
Instructions for MSiccDev/ai-context-kit, covering ai context kit agent guide, purpose, source of truth and precedence, repository map and scope and precedence for agents.md files.
codemap CLAUDE.md
Instructions for JordanCoin/codemap, covering 🛑 stop — run codemap before any task, repo root requirement (critical) and required usage.
llm-ide-rules pytest-integration-tests.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering pytest integration tests and example integration test.
Awesome-Prompt-Engineering contribution-review.instructions.md
Instructions for natnew/Awesome-Prompt-Engineering, covering reviewing pull requests and issues, tone, how to respond, explaining quality concerns and maintainer judgement.
elephant-agent copilot-instructions.md
Copilot instructions for agentic-in/elephant-agent, covering github copilot instructions, source of truth order, review priorities, harness-specific checks and validation expectations.
loadout shell.instructions.md
Shell Script Engineering Instructions (Bash, CLI wrappers, automation).