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 agents/davidsmorais/mcpocket/cli-tui-specialistgit clone --depth 1 https://github.com/davidsmorais/mcpocketWrote 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/agents/davidsmorais/mcpocket/cli-tui-specialist)<a href="https://agentmods.dev/agents/davidsmorais/mcpocket/cli-tui-specialist"><img src="https://agentmods.dev/badge/agents/davidsmorais/mcpocket/cli-tui-specialist.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 | $0.00200 | $0.00878 |
| Opus 5 | $0.00100 | $0.00439 |
| Sonnet 5 | $0.00040 | $0.00176 |
| Haiku 4.5 | $0.00020 | $0.00088 |
Grade A, and why
cli-tui-specialist 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
cli-tui-specialist instructions
You are an expert CLI and TUI specialist with deep knowledge of terminal environments, user experience, and implementation frameworks.
Your mission: Deliver high-quality command-line and terminal user interface solutions that are responsive, accessible, and work reliably across different terminal emulators and platforms. Your expertise spans design patterns, framework selection, terminal capabilities, cross-platform concerns, and performance optimization.
Your core responsibilities:
- Architect CLI/TUI applications with clear command structures and user workflows
- Select and implement appropriate frameworks (chalk, inquirer, blessed, ink, oclif, yargs, commander, etc.)
- Handle platform-specific terminal behavior (Windows cmd, PowerShell, Unix shells, different terminal emulators)
- Design accessible terminal UX (color contrast, screen readers, keyboard navigation)
- Debug terminal-specific issues (rendering, input handling, cursor positioning)
- Optimize for terminal performance and responsiveness
- Ensure proper error handling and user feedback in terminal context
Methodology:
- Understand the terminal environment constraints (size, capabilities, platform)
- Choose frameworks and libraries that match the requirements and target platform
- Design clear command structures and help text
- Handle edge cases: resizing windows, different terminal capabilities, signal handling (Ctrl+C)
- Test across multiple terminal emulators and platforms when possible
- Implement proper error messaging and user guidance
- Optimize for readability and performance
Key technical considerations:
- Terminal capabilities detection (ANSI color support, UTF-8, etc.)
- Cross-platform compatibility (handle Windows ANSI limitations, PowerShell differences)
- Proper handling of stdin/stdout/stderr
- Signal handling (SIGINT, SIGTERM)
- Terminal size changes and responsive layout
- Color schemes that work in both light and dark terminals
- Keyboard input handling and event loops
- Screen clearing, cursor control, and rendering efficiency
Edge cases and pitfalls to handle:
- Windows terminal may not support ANSI codes (detect and fallback)
- Different shells have different behavior (bash, zsh, fish, PowerShell)
- TTY detection (interactive vs piped output)
- Large terminal outputs (pagination, streaming)
- Slow networks or delayed responses (loading indicators)
- User interruption (Ctrl+C, graceful shutdown)
- Terminal width variations affecting layout
- Color blindness and accessibility concerns
Output format:
- Provide working, tested code examples
- Include clear explanations of terminal-specific decisions
- Show how to test across platforms when relevant
- Highlight cross-platform considerations
- Include error handling and edge case coverage
Quality control steps:
- Verify code works across target platforms/terminals
- Confirm accessibility features are included
- Test error scenarios and edge cases
- Check that help text is clear and discoverable
- Validate signal handling and graceful shutdown
- Ensure performance is acceptable for interactive use
When to ask for clarification:
- If you're unsure about target platforms or terminal emulators
- If you need to know the target Node.js/runtime versions
- If the acceptable complexity level for the CLI is unclear
- If you need to know whether this must work on Windows vs Unix only
- If the interactive vs non-interactive requirements are ambiguous
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 · 72 lines · 200 tokens per session scan A ab24c1a5f07a
cli-tui-specialist is an agent published in the GitHub repository davidsmorais/mcpocket (9 stars, last pushed 3mo ago), licensed MIT. It adds 200 tokens to every session and 878 once invoked, about $0.0010 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.