ariadne: Instructions file for Claude Code

CLAUDE.md

ariadne CLAUDE.md is an instructions file for Claude Code from CRJFisher/ariadne. It costs 1,330 tokens per session, scanned A, original, MIT.

Repository instructions for Ariadne, a project designed to trace call graphs and identify where a codebase starts running. A call graph maps which parts of a program call other parts.

In plain words
What is it for?
Use them when changing the project’s folder structure, names, documentation, or processing pipeline, especially before refactoring its information architecture.
Why use it?
They keep refactoring tied to the project’s main purpose and discourage unrelated code that makes the structure harder to understand and review.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is CRJFisher/ariadne's own configuration. It tells Claude Code how to work on ariadne 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 ariadne configures →

Reuse

Borrowing it

Nothing to install: this file belongs to CRJFisher/ariadne. 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/CRJFisher/ariadne/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/CRJFisher/ariadne

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 ariadne CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/crjfisher/ariadne/claude-md/github.svg)](https://agentmods.dev/instructions/crjfisher/ariadne/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/crjfisher/ariadne/claude-md"><img src="https://agentmods.dev/badge/instructions/crjfisher/ariadne/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.

agentmods 80×15 button for ariadne CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/crjfisher/ariadne/claude-md"><img src="https://agentmods.dev/badge/instructions/crjfisher/ariadne/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,330 This file is loaded in full into every session.
When invoked 1,330 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01330 $0.01330
Opus 5 $0.00665 $0.00665
Sonnet 5 $0.00266 $0.00266
Haiku 4.5 $0.00133 $0.00133

Measured 9d ago against content hash f48a338ce18b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ariadne 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 9d 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 · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guidelines

Goals

  • When refactoring, always investigate the existing information architecture beforehand. If the refactor will change the information architecture, then the refactor should include tasks to update and improve the information architecture.
  • The information architecture should follow the DDD principles.
  • Folders and file names should be expressive of the main, high-level action of the code within.

Project Layout / Intention Tree

  • the top of the intention tree (the actual purpose of this codebase) is to detect call graphs and thereby find the entry point to the codebase.
  • every change to the code needs to be justified in terms of its contribution to the top-level intention tree.
  • the module layout is the instantiation of the intention tree.
  • we never add 'extra' functionality outside of this intention tree, even if it is 'well-meaning' and 'might' be used one day. 'extra', surplus code reduces our longterm velocity. it is much better to spend effort reviewing narrow, focussed code and its integration, rather than trying to cover a wide surface area.
  • all namings and documentation should only reflect the trunk and branches of the intention tree, not the 'differential' changes we make to the codebase. E.g. if we're changing 'method_resolution.ts', we don't just create a file like 'enhanced_method_resolution.ts', we just improve 'method_resolution.ts', leaving the core intention tree intact.

Refactoring Ethos

  • DO NOT SUPPORT BACKWARD COMPATIBILITY - JUST CHANGE THE CODE.

Processing Pipeline

The core pipeline has three stages. Subsystem-specific guidance lives in .claude/rules/.

  1. Per-file indexing (index_single_file/) — 4-pass semantic indexing: query tree → scopes → definitions → references
  2. Project resolution (project/ + resolve_references/) — Registry updates + 2-phase resolution: name resolution → call resolution
  3. Entry point detection (trace_call_graph/) — Build call graph, identify unreachable functions

Read the full file on GitHub · 127 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. 9d ago First seen · 127 lines · 1,330 tokens per session scan A f48a338ce18b

Subscribe to this mod's changes

ariadne CLAUDE.md is an instructions file published in the GitHub repository CRJFisher/ariadne (22 stars, last pushed 5d ago), licensed MIT. It adds 1,330 tokens to every session, about $0.0066 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.