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/trycua/cua/claude-mdgit clone --depth 1 https://github.com/trycua/cuaWhat 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 | $0.00011 | $0.00011 |
| Opus 5 | $0.00005 | $0.00005 |
| Sonnet 5 | $0.00002 | $0.00002 |
| Haiku 4.5 | $0.00001 | $0.00001 |
Grade A, and why
cua 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 3d 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.
What it actually says
Claude Code project guidance
@AGENTS.md
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.
- 3d ago First seen · 4 lines · 11 tokens per session scan A 02570c5da5a2
cua CLAUDE.md is an instructions file published in the GitHub repository trycua/cua (22,024 stars, last pushed 3d ago), licensed MIT. It adds 11 tokens to every session, about $0.0001 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.
Other instructions, from other repositories
microsandbox AGENTS.md
AGENTS.md instructions for superradcompany/microsandbox, covering agents.md, scope, project map, design principles and backward compatibility review.
apple-mail-mcp CLAUDE.md
Instructions for sweetrb/apple-mail-mcp, covering claude.md - apple mail mcp server, configuring imap / smtp (when a user asks to set it up), critical: backslash escaping, why this matters and examples.
the-unofficial-swift-programming-language-skill CLAUDE.md
Instructions for kylehughes/the-unofficial-swift-programming-language-skill, covering claude.md, repository purpose, build commands, generate the skill package and build options.
apple-photos-mcp CLAUDE.md
Instructions for sweetrb/apple-photos-mcp, covering claude.md - apple photos mcp server, related documentation, first-run requirements, performance model: cold vs warm calls and the core workflow: query, then act.
pyapple-mcp CLAUDE.md
Instructions for 54yyyu/pyapple-mcp, covering claude.md, development commands, installation and development setup, install in development mode with dev dependencies and run the mcp server directly.
orchard-mcp AGENTS.md
Instructions for l22-io/orchard-mcp, covering agents.md, project overview, commands, architecture and key patterns.