test-forestui

Instructions for using tu, a tool that lets an agent see and interact with a terminal application in a headless environment, to test forestui. It requires checking the tool and tmux settings before using them.

In plain words
What is it for?
Building forestui, launching the compiled program, and visually checking its behavior and interface through terminal-driven tests.
Why use it?
Normal linting and type checks may not reveal visual problems, incorrect window names, or broken interactions.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/flipbit03/forestui/test-forestui
Any agent
npx skills add flipbit03/forestui --skill test-forestui
Clone the repo
git clone --depth 1 https://github.com/flipbit03/forestui

Made for: Claude Code, Codex.

Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,152 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
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 $0.00136 $0.02152
Opus 5 $0.00068 $0.01076
Sonnet 5 $0.00027 $0.00430
Haiku 4.5 $0.00014 $0.00215

Measured 2d ago against content hash 1d4b16d9619d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

test-forestui scanned grade C 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf $FUI_TEST_DIR
.claude/skills/test-forestui/SKILL.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self-drive forestui with tu

You can launch, see, and interact with forestui in headless virtual terminals using tu (terminal-use). This gives you the ability to visually verify your own code changes without the user needing to test manually.

Use this whenever you're developing forestui and want to confirm your changes work. Design your own test approach based on what you changed — there is no fixed test suite. You are the tester.

FIRST: bootstrap context

Before doing ANYTHING else, run these two commands and read their output. Do NOT skip. Do NOT proceed until both are in context.

tu usage
cat ~/.tmux.conf 2>/dev/null || echo "NO_TMUX_CONF"

From tu usage: learn all commands, key syntax, wait conditions. From .tmux.conf: learn the user's tmux prefix and all keybindings. Translate tmux bind syntax to tu press key names yourself from these two sources. If no .tmux.conf: defaults are prefix Ctrl+B, next Ctrl+B n, prev Ctrl+B p.

How to launch forestui

Build first. forestui is a Rust binary and ensure_tmux re-executes it, so you must drive the built executable, not cargo run:

export PATH="$HOME/.cargo/bin:$PATH"
cargo build            # in the project root
FUI_CMD=<project-root>/target/debug/forestui

NEVER launch forestui or any tmux command without TMUX_TMPDIR isolation. NEVER call tmux directly from Bash — not even with TMUX_TMPDIR set. The user is likely running their own tmux/forestui session right now. Any direct tmux call risks connecting to (and corrupting) their live session. ALL interaction with the test tmux must go through tu commands.

FUI_TEST_DIR=$(mktemp -d)

tu run --name fui --env TMUX_TMPDIR=$FUI_TEST_DIR \
  --cwd <project-root> -- env -u TMUX $FUI_CMD

tu wait --name fui --text "forestui" --timeout 15000

Pass a throwaway forest directory as an argument ($FUI_CMD /tmp/some-forest) so tests never touch the user's real ~/forest.

When you need to detach and reattach

Read the full file on GitHub · 209 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. 2d ago First seen · 209 lines · 0 tokens per session scan C 1d4b16d9619d

Subscribe to this mod's changes

test-forestui is a skill published in the GitHub repository flipbit03/forestui (25 stars, last pushed 5d ago), licensed MIT. It adds 136 tokens to every session and 2,152 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.