Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/arpitbbhayani/ape-skills/ape-cli-terminal-experience)<a href="https://agentmods.dev/skills/arpitbbhayani/ape-skills/ape-cli-terminal-experience"><img src="https://agentmods.dev/badge/skills/arpitbbhayani/ape-skills/ape-cli-terminal-experience/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/arpitbbhayani/ape-skills/ape-cli-terminal-experience"><img src="https://agentmods.dev/badge/skills/arpitbbhayani/ape-skills/ape-cli-terminal-experience.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 | $0.00141 | $0.10531 |
| Opus 5 | $0.00071 | $0.05266 |
| Sonnet 5 | $0.00028 | $0.02106 |
| Haiku 4.5 | $0.00014 | $0.01053 |
Grade C, and why
ape-cli-terminal-experience scanned grade C with 2 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 12d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
**EOF on a prompt.** Piped stdin, CI, cron, `curl | sh`. This is the most-missed case in Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**EOF on a prompt.** Piped stdin, CI, cron, `curl | sh`. This is the most-missed case in How it starts
The opening of the file, as written. The whole thing — 1,033 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Terminal Experience
A terminal UI that reads like Claude Code: mostly grey, a few deliberate accents, one line per fact, animation only while something is actually happening, and a plain-text fallback the moment the output stops being a terminal.
Every rule below is enforceable and testable. Follow them exactly rather than approximating the vibe.
1. The two laws
Subtle by default. Colour marks meaning -- a failure, a value the user will act on -- and nothing else. Labels, units, paths, and chrome are dim; values are plain. A full screen of output should read as mostly grey with a handful of accents, never as a colour test page. If you cannot say what a colour means, remove it.
Plain when not a terminal. Pipe the program anywhere and every escape sequence disappears, glyphs fall back to bracketed ASCII, rules vanish, and the spinner goes silent. Output stays greppable; a script parsing it never sees a byte of styling.
Three consequences that people get wrong:
- Colour detection and terminal detection are different questions.
FORCE_COLORshould add colour to piped output, but carriage-return redraws still make no sense there. Gate colour oncolor_enabled(), gate animation onis_tty(). - Only colour is a colour question. Glyph shape, rules, and the spinner are terminal
questions -- they gate on
is_tty(). Conflating the two is the single most common bug in this module:NO_COLOR=1in a real terminal then degrades✓to[OK], andFORCE_COLOR=1 | catdraws a horizontal rule into a pipe.--no-coloron a terminal must keep✓and keep the rule, and just drop the escapes. --jsonoutput is data. Turn colour off for it globally, never decorate it.
2. One voice module
All user-facing output goes through a single presentation module (ui.py, ui.go,
ui.ts -- one file). Logic modules never call print. They raise typed errors and
return data; the CLI layer decides how it looks.
cli.py argument parsing, flag wiring, orchestration, the exit-code map
ui.py colours, glyphs, line shapes, listings, prompts, spinner, run()
everything pure functions and typed exceptions -- zero output calls
else
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.
- 12d ago First seen · 1,033 lines · 141 tokens per session scan C e03982b31f3e
ape-cli-terminal-experience is a skill published in the GitHub repository arpitbbhayani/ape-skills (40 stars, last pushed yesterday), licensed MIT. It adds 141 tokens to every session and 10,531 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
accessibility
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build landing pages, websites, dashboards, web components, or any frontend UI. Generates creative, polished code that avoids generic AI aesthetics.
prototype
Build a self-contained local prototype at .turbo/prototypes/ .html, drive it, and hand it to the user to settle unknowns that prose cannot answer. Use when the user asks to "prototype this", "build a prototype", "mock this up", "show me what it would look like", "let me try the interaction first", or when a decision…
user-experience
Apply a UX lens to a user-facing change: whether it serves the user's real goal and whether the path through it holds together, using the Understanding, Bridging, and Flowing contexts. Use when scoping, planning, or assessing any change that affects what a user sees or does. Loaded as a lens during planning and…
slop-eval
Objectively evaluate a UI/web design against the pols.dev anti-slop design law: detect catalogued slop tells with cited evidence, score 8 weighted axes (color, type, components, layout, motion, execution, signature, cohesion), and emit a Slop Report with a 0–100 Slop Index and grade. Use when the user asks to…
design-md-validator
Validate DESIGN.md files against the official Google specification using the @google/design.md CLI linter. Works with local files. Use when the user wants to lint a DESIGN.md, check spec compliance, find broken token references, verify WCAG contrast ratios, diff two versions, export tokens to Tailwind or DTCG format…