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 skills add MadAppGang/magus --skill tui-navigation-patternsgit clone --depth 1 https://github.com/MadAppGang/magusWrote 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/skills/madappgang/magus/tui-navigation-patterns)<a href="https://agentmods.dev/skills/madappgang/magus/tui-navigation-patterns"><img src="https://agentmods.dev/badge/skills/madappgang/magus/tui-navigation-patterns/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.
<a href="https://agentmods.dev/skills/madappgang/magus/tui-navigation-patterns"><img src="https://agentmods.dev/badge/skills/madappgang/magus/tui-navigation-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00055 | $0.06303 |
| Opus 5.5 | $0.00022 | $0.02521 |
| Sonnet 5.5 | $0.00011 | $0.01261 |
| Haiku 4.5 | $0.00006 | $0.00630 |
Grade A, and why
tui-navigation-patterns scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
mcp__plugin_terminal_mux__start-and-watch({ slot: 2, isolated: true, command: "man curl", pattern: "CURL", timeout: 10 }) How it starts
The opening of the file, as written. The whole thing — 558 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TUI Navigation Patterns
Key sequences and navigation patterns for common TUI applications. Use with
mcp__plugin_terminal_mux__send-keys.
Slot convention
Every tool addresses a pane by slot, an integer 1–64. The same number returns the same pane on every call; a slot is never the agent's own pane.
- Slot 1 is the visible helper pane beside the user. Use it when the user asked to see the app, or when the app needs a fixed screen size (isolated panes have no window and no fixed size — a layout-sensitive TUI belongs on slot 1).
- Slot 2 or higher with
isolated: trueruns the app where nobody can see it. That is the default for every example below: a REPL or editor the user did not ask to watch should not appear beside them. isolated: trueneeds an explicit slot on every tool. Omitting it produces:isolated needs a slot number, because a pane you cannot see must be addressable later.- A slot's kind is fixed at creation. Reusing slot 2 without
isolatedafter it was opened isolated errors withslot 2 is an isolated pane; close it or use another slot. - Finish with
mcp__plugin_terminal_mux__close-pane({ slot: 2 })→[{"slot":2,"action":"killed"}]. Callmcp__plugin_terminal_mux__list-slotsfirst when you may already hold slots (after compaction); it returns a bare array,[]when empty.
The lifecycle every TUI or REPL session below follows:
mcp__plugin_terminal_mux__start-and-watch({ slot: 2, isolated: true, command, pattern, timeout })
→ { slot: 2, created: true, event: "pattern:…", detail, elapsed, output, paneState }
mcp__plugin_terminal_mux__send-keys({ slot: 2, keys, literal }) // or run-in-repl for REPLs
mcp__plugin_terminal_mux__capture-pane({ slot: 2 }) // read the screen
mcp__plugin_terminal_mux__close-pane({ slot: 2 })
send-keys Parameter Guide
mcp__plugin_terminal_mux__send-keys takes a single keys string (not an array). The
literal flag controls interpretation:
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.
- 1mo ago Changed a195c812568d
- 1mo ago Changed 500ecb57a8f3
- 1mo ago Changed · -85 lines 6b42bcedbe05
- 1mo ago First seen · 643 lines · 55 tokens per session scan A 78818277f48d
tui-navigation-patterns is a skill published in the GitHub repository MadAppGang/magus (13 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 6,303 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.