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/wbopan/cui/claude-mdgit clone --depth 1 https://github.com/wbopan/cuiWrote 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/wbopan/cui/claude-md)<a href="https://agentmods.dev/instructions/wbopan/cui/claude-md"><img src="https://agentmods.dev/badge/instructions/wbopan/cui/claude-md.svg" alt="Measured on agentmods" 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 | $0.00700 | $0.00700 |
| Opus 5 | $0.00350 | $0.00350 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
cui 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 4d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Architecture
This directory contains comprehensive test coverage for CUI services.
Testing Philosophy
- Prefer real implementations over mocks when testing (per project guidelines)
- Comprehensive unit test coverage for all services (90%+ target)
- Mock Claude CLI using
tests/__mocks__/claudescript for consistent testing - Silent logging in tests (LOG_LEVEL=silent) to reduce noise
Test Structure
tests/
├── __mocks__
│ └── claude
├── integration
│ ├── conversation-status-integration.test.ts
│ ├── real-claude-integration.test.ts
│ └── streaming-integration.test.ts
├── setup.ts
├── unit
│ ├── cui-server.test.ts
│ ├── claude-history-reader.test.ts
│ ├── claude-process-long-running.test.ts
│ ├── claude-process-manager.test.ts
│ ├── cli
│ │ ├── get.test.ts
│ │ ├── list.test.ts
│ │ ├── serve.test.ts
│ │ ├── status-simple.test.ts
│ │ ├── status-working.test.ts
│ │ └── status.test.ts
│ ├── conversation-status-tracker.test.ts
│ ├── json-lines-parser.test.ts
│ └── stream-manager.test.ts
└── utils
└── test-helpers.ts
Mock Claude CLI
The project includes a mock Claude CLI (tests/__mocks__/claude) that:
- Simulates real Claude CLI behavior for testing
- Outputs valid JSONL stream format
- Supports various command line arguments
- Enables testing without requiring actual Claude CLI installation
Testing Patterns
// Integration test pattern with mock Claude CLI
function getMockClaudeExecutablePath(): string {
return path.join(process.cwd(), 'tests', '__mocks__', 'claude');
}
// Server setup with random port to avoid conflicts
const serverPort = 9000 + Math.floor(Math.random() * 1000);
const server = new CUIServer({ port: serverPort });
// Override ProcessManager with mock path
const mockClaudePath = getMockClaudeExecutablePath();
const { ClaudeProcessManager } = await import('@/services/claude-process-manager');
(server as any).processManager = new ClaudeProcessManager(mockClaudePath);
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.
- 4d ago First seen · 98 lines · 700 tokens per session scan A efebdb7cd0da
cui CLAUDE.md is an instructions file published in the GitHub repository wbopan/cui (1,144 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 700 tokens to every session, about $0.0035 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
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
slivingdoc AGENTS.md
AGENTS.md instructions for baalimago/slivingdoc, covering agents.md — slivingdoc, architecture, package map, event flow and startup wiring (main.go).