Borrowing it
Nothing to install: this file belongs to AvivAvital2/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.
curl -O https://raw.githubusercontent.com/AvivAvital2/Ariadne/main/CLAUDE.mdgit clone --depth 1 https://github.com/AvivAvital2/AriadneWrote 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.
[](https://agentmods.dev/instructions/avivavital2/ariadne/claude-md)<a href="https://agentmods.dev/instructions/avivavital2/ariadne/claude-md"><img src="https://agentmods.dev/badge/instructions/avivavital2/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.
<a href="https://agentmods.dev/instructions/avivavital2/ariadne/claude-md"><img src="https://agentmods.dev/badge/instructions/avivavital2/ariadne/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.03912 | $0.03912 |
| Opus 5 | $0.01956 | $0.01956 |
| Sonnet 5 | $0.00782 | $0.00782 |
| Haiku 4.5 | $0.00391 | $0.00391 |
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.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ariadne - Documentation Library for Claude
Ariadne generates and manages documentation that helps Claude understand codebases.
Documentation Layout
docs/ holds hand-written guides at the top level — e.g. new-project-onboarding.md, claude-code-integration.md, directory-scoping.md — which are authoritative and linked from the README (fine to read). Exported per-source docs under docs/{source}/ are generated and duplicate README/source content, so skip those to save context.
Quick Reference
Commands
uv run ariadne onboard # Full pipeline in one run: free phases + cost preview, then PROMPTS to continue into paid phases (no re-indexing)
uv run ariadne onboard --approve # Skip the proceed-prompt (non-interactive/CI); --live/--batch also skip the LLM-mode prompt
uv run ariadne dry-run # Estimate LLM cost of the pipeline; runs only the free phases, no API calls
uv run ariadne generate # Generate docs from source code
uv run ariadne export # Export ONE source-scoped zip artifact: ./docs/{source}.zip — only that source's docs travel (--no-archive writes the ./docs/{source}/ tree)
uv run ariadne import # Import from ./docs/{source}.zip when present, else ./docs/{source}/ — delta: identical docs are skipped; large embed runs PROMPT live-vs-batch + cost (--live/--batch pick the mode, --yes approves; batch = half price via OpenAI Batch API)
uv run ariadne rebuild # Rebuild embeddings (same live-vs-batch prompt on large runs; --live/--batch skip it, --yes skips the cost prompt)
uv run ariadne check # Check for stale documentation
uv run ariadne config # Show current configuration
uv run ariadne source add NAME --path DIR # Add/update a source in ariadne.yaml (no manual editing)
uv run ariadne source list # List configured sources
uv run ariadne source remove NAME # Remove a source from ariadne.yaml
uv run ariadne finding "text" # Save a session finding/conclusion
uv run ariadne sync # Catch up with git changes since last sync
uv run ariadne merge --dry-run # Preview post-merge doc regeneration
uv run ariadne merge # Regenerate stable docs after branch merge
uv run ariadne usage # Show usage statistics (last 30 days)
uv run ariadne gaps # Show documentation gap analysis
uv run ariadne gaps --analyze # LLM-powered gap recommendations
uv run ariadne testimonials # Show top-scored Q&A from the local best-of store
uv run ariadne mcp # Start MCP server (stdio transport)
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.
- 9d ago First seen · 206 lines · 3,912 tokens per session scan A 37ff84dcebb0
Ariadne CLAUDE.md is an instructions file published in the GitHub repository AvivAvital2/Ariadne (4 stars, last pushed 23d ago), licensed Apache-2.0. It adds 3,912 tokens to every session, about $0.0196 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.