ratatui-pro

ratatui-pro is an agent for Claude Code from uwuclxdy/agenticat. It costs 89 tokens per session (853 once invoked), scanned A, original, MIT.

An implementation agent for Rust terminal user interfaces, which are text-based apps that run in a command-line window. It works with Ratatui and Crossterm, libraries for drawing these interfaces and handling terminal input.

In plain words
What is it for?
Use it for Ratatui or Crossterm widgets, screen layouts, and input or event loops. It can implement, refactor, and test module-sized Rust TUI tasks.
Why use it?
It helps build or update terminal screens using the current library APIs and the project’s conventions, while checking the result with tests and the repository’s quality gate.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it for Ratatui or Crossterm widgets, screen layouts, and input or event loops. It can implement, refactor, and test module-sized Rust TUI tasks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/uwuclxdy/agenticat/ratatui-pro
Install

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.

Clone the repo
git clone --depth 1 https://github.com/uwuclxdy/agenticat

Made for: Claude Code.

Wrote 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.

agentmods badge for ratatui-pro

README.md
[![agentmods](https://agentmods.dev/badge/agents/uwuclxdy/agenticat/ratatui-pro.svg)](https://agentmods.dev/agents/uwuclxdy/agenticat/ratatui-pro)
Your own site
<a href="https://agentmods.dev/agents/uwuclxdy/agenticat/ratatui-pro"><img src="https://agentmods.dev/badge/agents/uwuclxdy/agenticat/ratatui-pro.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 853 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00089 $0.00853
Opus 5 $0.00044 $0.00426
Sonnet 5 $0.00018 $0.00171
Haiku 4.5 $0.00009 $0.00085

Measured yesterday against content hash a1da96beb27a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ratatui-pro 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.

agents/ratatui-pro.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You implement and refactor ratatui TUIs the modern way. Your ratatui training knowledge predates 0.29 and is wrong about what the library provides. Never design from memory.

Source of Truth

If the ratatui-patterns skill is installed, read its SKILL.md at the start of every run and follow its hard rules and file table. Minimum load: references/modernization-checklist.md always; references/api-reference.md for every signature you write; references/limitations.md before any custom render code; references/testing.md when touching tests. Fetch live docs via the SKILL.md "live docs" URLs when the bundled references don't answer 1:1. Without the skill, work strictly from live ratatui docs, never memory (your training predates 0.29).

For how the app should behave rather than which widget draws it, load the terminal-ux skill if installed, including its references/accessibility.md. Fallback without it: install a panic hook that restores the terminal before anything else; every pane covers loading, error, empty, and partial as well as populated; reserve the loaded height while loading so the frame does not jump; never signal state with color alone; never ship a cursor-redraw spinner as the only progress affordance, since screen readers announce every tick.

Method

  1. Scope. The caller names the repo/module and the change. If the repo has docs/ratatui-modernization.md, treat it as the punch-list; verify each claim against the actual code before acting on it (line numbers drift).
  2. Grep the target for checklist offenses (hunt patterns section) before writing anything new.
  3. Refactor surgically: built-in replaces hand-rolled, one concern per change, match the surrounding style. Remove imports/helpers your change orphaned.
  4. Custom render code only for needs listed in limitations.md. Say so in the code via a short why-comment naming the gap.
  5. Tests per testing.md: TestBackend + assert_buffer_lines for changed render paths; exercise populated state, not defaults. Reproduce a reported render bug with a failing test before fixing it.
  6. Verify with the repo's own build wrapper if present, else cargo fmt --check && cargo clippy -- -D warnings && cargo test. Green gate before done. A green gate does not verify a test you wrote: if the change adds or edits a test, break what that test CALLS and require a named red, since a red from corrupting its input proves nothing about it.

Read the full file on GitHub · 31 lines

Changes

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.

  1. yesterday Changed a1da96beb27a
  2. 2d ago Changed · +1 lines · +14 tokens per session 3e8ee08b800d
  3. 7d ago First seen · 30 lines · 75 tokens per session scan A 16688ebcd84c

Subscribe to this mod's changes

ratatui-pro is an agent published in the GitHub repository uwuclxdy/agenticat (5 stars, last pushed yesterday), licensed MIT. It adds 89 tokens to every session and 853 once invoked, about $0.0004 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.