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/kellymears/arcana-cli/claude-mdgit clone --depth 1 https://github.com/kellymears/arcana-cliWhat 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 | $0.00389 | $0.00389 |
| Opus 5 | $0.00195 | $0.00195 |
| Sonnet 5 | $0.00078 | $0.00078 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
arcana-cli 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 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.
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.md
Project overview
Arcana CLI — a terminal tarot reading application built with Ink (React for CLIs). TypeScript, ES Modules, Node 24+.
Architecture
src/cli.tsx— Entry point. Calls Ink'srender()with the root<App />component.src/app.tsx— Root component. All UI flows from here.dist/— Compiled output (gitignored). Thedist/cli.jsbinary is the executable.
Ink components use <Box> for layout (flexbox) and <Text> for styled text output. Think React but rendering to the terminal.
Key conventions
- ESM only —
"type": "module"in package.json. All imports use.jsextensions (NodeNext resolution requires this even for.tsxsource files). - Automatic JSX runtime —
jsx: "react-jsx"in tsconfig. Do not addimport Reactto component files. - Strict TypeScript — strict mode is enabled.
- Import sorting — eslint-plugin-perfectionist enforces natural sort order on imports, exports, object keys, and JSX props. Sort alphabetically.
- Prettier — double quotes, semicolons, trailing commas, 2-space indent, 80 char width.
Commands
npm run build— Compile TypeScript todist/npm run dev— Watch modenpm start— Run the CLInpm run lint— ESLintnpm run format— Prettier writenpm run format:check— Prettier check
Verification
After making changes, always run:
npm run build && npm start && npm run lint && npm run format:check
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 · 39 lines · 389 tokens per session scan A bf3e26b1b0de
arcana-cli CLAUDE.md is an instructions file published in the GitHub repository kellymears/arcana-cli (0 stars, last pushed 5mo ago), licensed ISC. It adds 389 tokens to every session, about $0.0019 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
cookd CLAUDE.md
Instructions for codeclowns01/cookd, covering claude map protocol, every session — do this before anything else, before making any change, step 1 — check the guardrails and step 3 — walk the downstream list (interface changes only).
claude-make-it-rain CLAUDE.md
Instructions for gceico/claude-make-it-rain, covering claude.md, commands, architecture, conventions & invariants and testing.
campy AGENTS.md
Instructions for dropdevrahul/campy, covering campy - opencode pets plugin, project overview, available pets, file structure and commands.
pump-fun-sdk CLAUDE.md
Claude Code instructions for nirholas/pump-fun-sdk, covering pump sdk — claude code instructions, behavior rules, architecture (read this), official pump protocol docs (must read) and code examples.
pump-fun-sdk AGENTS.md
AGENTS.md instructions for nirholas/pump-fun-sdk, covering pump sdk — agent development guidelines, project overview, architecture, on-chain programs and official pump protocol docs.
pump-fun-sdk GEMINI.md
Gemini CLI instructions for nirholas/pump-fun-sdk, covering pump sdk — gemini instructions, project overview, key directories, on-chain programs and official pump protocol docs.