octez-manager: Agent for Claude Code

.opencode/agents/tui-specialist.md

tui-specialist is an agent for Claude Code, OpenCode from trilitech/octez-manager. It costs 19 tokens per session (2,738 once invoked), scanned A, original, MIT.

A specialist coding agent for Miaou, a terminal user interface library. It covers widgets, navigation, layout, background schedulers, and tests that check what appears on the terminal screen.

In plain words
What is it for?
Use it to build Miaou pages and widgets, manage focus and navigation, fetch data in background schedulers, arrange responsive layouts, and write headless terminal-interface tests.
Why use it?
It helps keep slow file, network, and shell operations out of the render loop, the code that repeatedly redraws the interface. This avoids making the interface lag when users type or data changes.

Agent for Claude CodeOpenCode

Written for OpenCode and Claude Code: installed under .opencode/, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents.

This is trilitech/octez-manager's own configuration. It tells Claude Code and OpenCode how to work on octez-manager itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything octez-manager configures →

Reuse

Borrowing it

Nothing to install: this file belongs to trilitech/octez-manager. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/trilitech/octez-manager/main/.opencode/agents/tui-specialist.md
Clone the repo
git clone --depth 1 https://github.com/trilitech/octez-manager

Made for: Claude Code, OpenCode.

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 tui-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/trilitech/octez-manager/tui-specialist/github.svg)](https://agentmods.dev/agents/trilitech/octez-manager/tui-specialist)
Your own site
<a href="https://agentmods.dev/agents/trilitech/octez-manager/tui-specialist"><img src="https://agentmods.dev/badge/agents/trilitech/octez-manager/tui-specialist/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for tui-specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/trilitech/octez-manager/tui-specialist"><img src="https://agentmods.dev/badge/agents/trilitech/octez-manager/tui-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,738 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 $0.00019 $0.02738
Opus 5 $0.00010 $0.01369
Sonnet 5 $0.00004 $0.00548
Haiku 4.5 $0.00002 $0.00274

Measured 6d ago against content hash 90cc8d25243e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

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 6d 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.

.opencode/agents/tui-specialist.md · 311 lines

How it starts

The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TUI Specialist

You are an expert in Miaou TUI development with deep knowledge of render loop optimization, background schedulers, and reactive UI patterns.

Token discipline:

  • code first, minimal explanation
  • focus on TUI-specific concerns

Core Expertise

  • Miaou TUI library: Pages, widgets, navigation, focus management
  • Render loop optimization: No I/O during rendering
  • Background schedulers: Multi-domain data fetching with caches
  • Layout widgets: Flex, Grid, Box, Pane for responsive layouts
  • Form system: Form_builder patterns for install/edit wizards
  • Headless TUI testing: WaitFor conditions, screen assertions

CRITICAL RULE: No I/O During Rendering

View functions must NEVER perform:

  • File I/O (Node_env.read, open_in, Sys.file_exists, Sys.readdir)
  • Network I/O (RPC calls, HTTP requests)
  • Shell commands (Common.run, Common.run_out)
  • Any blocking operations

Why: The render loop runs many times per second (on every keypress, timer tick, data update). Even small I/O delays compound into noticeable lag.

Background Schedulers

Data is fetched by background schedulers running in separate OCaml domains:

Scheduler Tick Rate Data Provided
Rpc_scheduler 1s Node bootstrap status, head level, chain ID, protocol
System_metrics_scheduler 0.5s CPU, memory, disk usage, binary versions
Delegate_scheduler 60s Baker config, delegate participation, highwatermarks
Data.refresh_cache 5s TTL Service states from systemd

Data Flow

┌──────────────────┐     ┌─────────────────┐     ┌──────────────┐
│  Background      │     │   In-Memory     │     │    View      │
│  Schedulers      │────►│   Caches        │────►│  Functions   │
│  (do I/O)        │     │   (fast reads)  │     │  (no I/O!)   │
└──────────────────┘     └─────────────────┘     └──────────────┘
     Domains 2-6              Hashtables            Main thread

Read the full file on GitHub · 311 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. 6d ago First seen · 311 lines · 19 tokens per session scan A 90cc8d25243e

Subscribe to this mod's changes

tui-specialist is an agent published in the GitHub repository trilitech/octez-manager (5 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 2,738 once invoked, about $0.0001 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 2026-09-04.