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 | $0.04077 | $0.04077 |
| Opus 5.5 | $0.01631 | $0.01631 |
| Sonnet 5.5 | $0.00815 | $0.00815 |
| Haiku 4.5 | $0.00408 | $0.00408 |
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 16d 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 — 212 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.
Its backend can use OpenAI, Anthropic or the fixed local Qwen pair independently of the consuming agent's model. See supported models for configuration, credentials and verification scope.
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.
- 16d ago Changed · +6 lines · +165 tokens per session 8c675aeed197
- 2mo 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 13d ago), licensed Apache-2.0. It adds 4,077 tokens to every session, about $0.0163 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 2026-08-31.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.