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 wan-huiyan/cutify-this --skill cutify-that-terminalgit clone --depth 1 https://github.com/wan-huiyan/cutify-thisWrote 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/wan-huiyan/cutify-this/cutify-that-terminal)<a href="https://agentmods.dev/skills/wan-huiyan/cutify-this/cutify-that-terminal"><img src="https://agentmods.dev/badge/skills/wan-huiyan/cutify-this/cutify-that-terminal/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/wan-huiyan/cutify-this/cutify-that-terminal"><img src="https://agentmods.dev/badge/skills/wan-huiyan/cutify-this/cutify-that-terminal.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00259 | $0.03287 |
| Opus 5 | $0.00130 | $0.01643 |
| Sonnet 5 | $0.00052 | $0.00657 |
| Haiku 4.5 | $0.00026 | $0.00329 |
Grade A, and why
cutify-that-terminal 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cutify That Terminal ✨
Make the window you stare at all day pleasant to look at — a theme, a rounded font, a prompt that tells you the branch you are on — and then prove every glyph actually renders before calling it done. That last part is the whole point of this skill. Everything else here is four Homebrew commands.
Problem
Terminal ricing guides all end the same way: install a Nerd Font, paste this
config, enjoy. None of them verify. So the user pastes it, the prompt comes
back with ? boxes where the icons should be, and there is no error message
anywhere to explain it — because nothing errored. A font name that matches
nothing falls back silently. A preset that leaves one icon behind still
loads fine. A terminal that was never given the font just draws boxes.
The user cannot debug this, because every layer reports success.
Context / Trigger conditions
Use when any of:
- "make my terminal cuter / prettier / nicer / less ugly", "my terminal is boring".
- A theme by name: Catppuccin, Rosé Pine, Tokyo Night, Gruvbox, Everforest, Nord, Dracula.
- "nicer prompt", "show the git branch in my prompt", "Starship", "Oh My Zsh", "Powerlevel10k".
- "Nerd Font", "powerline symbols", "what font should my terminal use".
- The bug: "my prompt shows question marks / boxes / weird symbols", "the icons are broken", "tofu", "it looks fine in one terminal but not the other".
- "which terminal should I use", Ghostty vs iTerm2 vs kitty vs WezTerm vs Warp.
Skip if: the platform is Linux or Windows (the ideas port, the commands do
not); the shell is not zsh; or the user wants a web page made cute — that is
sparkle-that-page, the sibling skill.
Before you touch anything — the safety contract
This skill differs from the rest of the cutify-this bundle in one way that
matters: the others drop a file into a project and revert by deleting it. This
one installs software and edits the user's shell config. A broken .zshrc
means a shell that will not start. So:
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 272 lines · 259 tokens per session scan A f6caa34dcab0
cutify-that-terminal is a skill published in the GitHub repository wan-huiyan/cutify-this (1 stars, last pushed 28d ago), licensed MIT. It adds 259 tokens to every session and 3,287 once invoked, about $0.0013 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.
Other skills, from other repositories
claude-code-bash-patterns
Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.
sitrep-panel
Keep a live local HTML report updated as you work on a task — a status board, a running "what's happening now" narrative, screenshots, and a newest-first log — served on localhost so the user can watch progress in a browser tab instead of reading the transcript. Use when the user invokes /sitrep-panel, asks for a…
promote
Turn a scratch script into a permanent tool this repo keeps. Use when a check, report, or analysis has proved worth running more than once.
parallel-session-coedit-via-source-mtime-and-idempotent-rebuild
Edit a shared deliverable while another live session or a colleague's agent is editing the same file right now — "don't delete each other's work", "only write when the other one is finished". When the file is built from many per item sources by an assembler (sections into one HTML, slides, reports): source mtime shows…
fan-out-cost-control
Dispatching a fan-out of agents: ban per-agent advisor() calls (check judgement once at the merge, not per shard), make agents append output as they go, and don't kill a fan-out past its costly stage — a killed agent returns nothing, a limit-killed one resumes from disk.
finito
Closes a working session with a coding agent and produces the full closing package: a numbered summary anyone can read, the next steps, what got written down, the real state of the repository including what is left to push, and two blocks the next session resumes from, one to paste after /compact and one to open a…