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 skills/utensils/mold/tui-uatnpx skills add utensils/mold --skill tui-uatgit clone --depth 1 https://github.com/utensils/moldWrote 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/utensils/mold/tui-uat)<a href="https://agentmods.dev/skills/utensils/mold/tui-uat"><img src="https://agentmods.dev/badge/skills/utensils/mold/tui-uat.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 5.1 | $0.00040 | $0.05400 |
| Opus 5 | $0.00020 | $0.02700 |
| Sonnet 5 | $0.00008 | $0.01080 |
| Haiku 4.5 | $0.00004 | $0.00540 |
Grade C, and why
tui-uat scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
trap 'scripts/tui-uat.sh cleanup >/dev/null 2>&1 || true; [ -n "${MOLD_HOME:-}" ] && rm -rf "$MOLD_HOME"' EXIT INT TERM How it starts
The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TUI Acceptance Testing via Ghostty
Run the mold TUI inside a native Ghostty terminal window for automated acceptance testing. Uses Ghostty 1.3+ AppleScript API for real terminal rendering — proper fonts, true colors, and pixel-perfect screenshots with no conversion artifacts.
Prerequisites
- Ghostty 1.3+ with
macos-applescript = true(default) - A debug build of mold with TUI support:
cargo build -p mold-ai --features tui
Or use the devshell helper: build
Helper Script
All TUI interaction goes through scripts/tui-uat.sh:
# Lifecycle
scripts/tui-uat.sh launch [--fresh] [--env K=V]* [--local] [--host URL]
scripts/tui-uat.sh quit # Close the tracked session's Ghostty window
scripts/tui-uat.sh cleanup # Reap any orphan mold-TUI Ghostty window (state-file-free)
scripts/tui-uat.sh status
scripts/tui-uat.sh env # Print MOLD_HOME / MOLD_DB_PATH
# Screen I/O
scripts/tui-uat.sh capture # Print current screen (plain text)
scripts/tui-uat.sh screenshot [output.png]
scripts/tui-uat.sh view <1-5|name> # 1=Create 2=Library 3=Models 4=Machines 5=Settings; 'chain' opens the Create chain composer
scripts/tui-uat.sh send <key>...
scripts/tui-uat.sh wait-for <pattern> [timeout]
scripts/tui-uat.sh assert <pattern>
# DB / persistence helpers
scripts/tui-uat.sh db [--write] [--force] <sql> # sqlite3 against session DB
scripts/tui-uat.sh db-get <key> # One value from settings table
scripts/tui-uat.sh db-assert <key> <value> # Pass/fail equality check
scripts/tui-uat.sh db-dump # Pretty-print settings + model_prefs
# Settings helpers
scripts/tui-uat.sh settings-focus <appearance|configuration>
scripts/tui-uat.sh theme-set <slug> # studio-dark|studio-light|safelight-dark|safelight-light|mocha|latte|ristretto|gruvbox|tokyo|nord|dracula
# Model + per-model prefs helpers
scripts/tui-uat.sh model <name> # Full picker dance — Parameters → Model → type filter → Enter. Pass the exact `model:tag` to avoid matching the wrong variant.
scripts/tui-uat.sh db-model-assert <model> <col> <v> # Pass/fail on a single `model_prefs` column
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.
- 2d ago Changed c248387f98e1
- 6d ago First seen · 355 lines · 40 tokens per session scan C 10141c854cbe
tui-uat is a skill published in the GitHub repository utensils/mold (42 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 5,400 once invoked, about $0.0002 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.
Other skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
run-integration-tests
Build, pack, and run .NET MAUI integration tests locally. Validates templates, samples, and end-to-end scenarios using the local workload.
cli-e2e-testcase-writer
Use when adding or updating Go CLI E2E coverage for one tests/clie2e/{domain} domain of the compiled lark-cli, especially when the work requires live --help or schema exploration, scenario-based clie2e.RunCmd workflows, and per-domain coverage.md maintenance.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
__SKILL_ID__
This fixture verifies that skill content can be written into the target sandbox and queried back immediately.
kl-consistency-test
Write, calibrate, and debug the prefill-vs-decode logprob (KL) consistency tests in sglang -- the two independent conditions a zero requires (every operator batch-invariant, and the two paths computing the same function), which helper separates them, how to pick a threshold once they hold, and how to localize a…