What is ai-distiller CLAUDE.md?

A CLAUDE.md instruction file for AI Distiller, a command-line tool that reduces large codebases to the structure an AI can read more easily. It documents the tool's goals, supported output formats, and command examples.

Use it when working on the CLI, its language support, output formats, or options for removing selected code details.

It gives Claude project-specific context for developing and using the code-distilling command.

How janreges/ai-distiller configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to janreges/ai-distiller. 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/janreges/ai-distiller/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/janreges/ai-distiller

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/janreges/ai-distiller/claude-md/github.svg)](https://agentmods.dev/instructions/janreges/ai-distiller/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/janreges/ai-distiller/claude-md"><img src="https://agentmods.dev/badge/instructions/janreges/ai-distiller/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/janreges/ai-distiller/claude-md"><img src="https://agentmods.dev/badge/instructions/janreges/ai-distiller/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 9,205 This file is loaded in full into every session.

When invoked 9,205 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	$0.09205	$0.09205
Opus 5.5	$0.03682	$0.03682
Sonnet 5.5	$0.01841	$0.01841
Haiku 4.5	$0.00920	$0.00920

Measured 2mo ago against content hash ac199acb89a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-distiller 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 · 1,021 lines

How it starts

The opening of the file, as written. The whole thing — 1,021 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Distiller - Claude Development Instructions

Project Overview

AI Distiller is a high-performance CLI tool that extracts essential code structure from large codebases, making them digestible for LLMs by removing unnecessary details while preserving semantic information. Think of it as "code compression for AI context windows."

Key Project Goals

Single native binary - No runtime dependencies, works everywhere
Blazingly fast - Process 10MB codebase in <2 seconds
Multi-language support - 15+ languages via tree-sitter WASM
Flexible output - Text, Markdown, JSON, JSONL, XML formats
Granular control - Strip exactly what you don't need

CLI Interface Specification

The main CLI is aid (AI Distiller):

aid [path] [flags]

# Examples:
aid                                    # Process current directory
aid src/                              # Process src directory
aid main.py                           # Process single file
aid --comments=0,implementation   # Remove comments and implementations
aid --format json-structured --output api.json   # JSON output to file
aid --private=0 --protected=0 --internal=0 --stdout       # Print only public members to stdout

# Special git mode (activated when path is .git):
aid .git                              # Show full git history
aid .git --git-limit=50              # Show last 50 commits
aid .git --with-analysis-prompt      # Include AI analysis prompt for insights

# AI-powered analysis modes:
aid --ai-action=flow-for-deep-file-to-file-analysis     # Generate comprehensive task list
aid --ai-action=flow-for-multi-file-docs                # Generate documentation workflow
aid --ai-action=prompt-for-refactoring-suggestion       # Generate refactoring analysis prompt
aid --ai-action=prompt-for-complex-codebase-analysis    # Full codebase analysis with diagrams
aid --ai-action=prompt-for-security-analysis            # Security-focused analysis prompt
aid --ai-action=prompt-for-performance-analysis         # Performance optimization analysis
aid --ai-action=prompt-for-best-practices-analysis      # Best practices and code quality analysis
aid --ai-action=prompt-for-bug-hunting                  # Systematic bug hunting analysis
aid --ai-action=prompt-for-single-file-docs             # Single file documentation analysis
aid --ai-action=prompt-for-diagrams                     # Generate 10 beneficial Mermaid diagrams

# Legacy mode (deprecated):
aid --ai-analysis-task-list                    # Use --ai-action=flow-for-deep-file-to-file-analysis instead

Read the full file on GitHub · 1,021 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 · 1,021 lines · 9,205 tokens per session scan A ac199acb89a9

Subscribe to this mod's changes

ai-distiller CLAUDE.md is an instructions file published in the GitHub repository janreges/ai-distiller (172 stars, last pushed 5mo ago), licensed MIT. It adds 9,205 tokens to every session, about $0.0368 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 2026-08-30.

ai-distiller CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ai-distiller CLAUDE.mdjanreges/ai-distiller	Instructions file	172	5mo ago	MIT	A	9,205	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

ai-distiller: Instructions file for Claude Code