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/nuxt/ui/claude-mdgit clone --depth 1 https://github.com/nuxt/uiWhat 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 | $0.00026 | $0.00026 |
| Opus 5 | $0.00013 | $0.00013 |
| Sonnet 5 | $0.00005 | $0.00005 |
| Haiku 4.5 | $0.00003 | $0.00003 |
Grade C, and why
ui CLAUDE.md scanned grade C with 1 finding 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 yesterday.
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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Claude Code only auto-loads CLAUDE.md, so this imports the shared agent instructions. --> What it actually says
@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.
- yesterday First seen · 4 lines · 26 tokens per session scan C a07f6512fb1a
ui CLAUDE.md is an instructions file published in the GitHub repository nuxt/ui (6,861 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
foundry AGENTS.md
AGENTS.md instructions for incubrain/foundry, covering incubrain foundry, quick start, external consumer repos, testing layer changes in external consumers (verdaccio) and one-time setup.
foundry CLAUDE.md
Claude Code instructions for incubrain/foundry, covering context-mode — mandatory routing rules, blocked commands — do not attempt these, curl / wget — blocked, inline http — blocked and webfetch — blocked.
ui-components AGENTS.md
Instructions for starc007/ui-components, covering beui v2 — agent guide, commands, layout, component catalog and components (motion category — primitives).
OneJS AGENTS.md
Instructions for Singtaa/OneJS, covering onejs v3: agent guide, requirements, install, project setup and build and live reload.
mcp-toolkit AGENTS.md
Instructions for nuxt-modules/mcp-toolkit, covering agents.md, project overview, monorepo structure, development environment setup and prerequisites.
OneJS CLAUDE.md
Instructions for Singtaa/OneJS: Agent guidance for this repository lives in AGENTS.md. Read it first.