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/patchline-ai/aria/claude-mdgit clone --depth 1 https://github.com/Patchline-AI/AriaWhat 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 | $0.01329 | $0.01329 |
| Opus 5 | $0.00665 | $0.00665 |
| Sonnet 5 | $0.00266 | $0.00266 |
| Haiku 4.5 | $0.00133 | $0.00133 |
Grade A, and why
Aria 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 71 lines · 1,329 tokens per session scan A 50279c86b7fc
Aria CLAUDE.md is an instructions file published in the GitHub repository Patchline-AI/Aria (3 stars, last pushed 23d ago), with no licence file. It adds 1,329 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 2026-08-31.
Other instructions, from other repositories
mcp-score AGENTS.md
Instructions for tskovlund/mcp-score, covering mcp-score, architecture, why two approaches?, dev environment and commands.
itunes.vim CLAUDE.md
Claude Code instructions for chew-z/itunes.vim, covering claude.md, build commands, build binaries, cli usage and mcp server.
tidal-cli CLAUDE.md
Claude Code instructions for SteveGrosbois/tidal-cli, covering tidal-cli development guidelines, active technologies, project structure, commands and code style.
kobox CLAUDE.md
Claude Code instructions for yangyue1974/kobox, covering installing kobox (instructions for claude code), steps and troubleshooting.
dj-claude-plugin CLAUDE.md
Claude Code instructions for p-poss/dj-claude-plugin, covering dj claude, playing music without an api key, tools, playback and jam session.
mcp-score CLAUDE.md
Instructions for tskovlund/mcp-score, a project described as: MCP server for AI-driven music score generation and manipulation. Natural language to notation via MusicXML + live MuseScore integration.