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 decodingai-magazine/building-a-coding-agent-from-scratch-course --skill demo-1-terminal-arcadegit clone --depth 1 https://github.com/decodingai-magazine/building-a-coding-agent-from-scratch-courseWrote 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/decodingai-magazine/building-a-coding-agent-from-scratch-course/demo-1-terminal-arcade)<a href="https://agentmods.dev/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/demo-1-terminal-arcade"><img src="https://agentmods.dev/badge/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/demo-1-terminal-arcade/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/decodingai-magazine/building-a-coding-agent-from-scratch-course/demo-1-terminal-arcade"><img src="https://agentmods.dev/badge/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/demo-1-terminal-arcade.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 | $0.00046 | $0.00752 |
| Opus 5 | $0.00023 | $0.00376 |
| Sonnet 5 | $0.00009 | $0.00150 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
demo-1-terminal-arcade 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 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.
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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build a playable, colorful game of Snake that runs in the terminal, as a single self-contained
Python file .decode/outputs/snake.py (unless the human named a different path).
Constraints
- Pure standard library only — use the built-in
cursesmodule for rendering and input. Add zero third-party dependencies (nothing that would needuv addorpip install). - Keep it small and readable: roughly 250 lines. This is a demo people will read, not just play.
Plan first
Before writing any code, lay out your steps with todo_write (draw field → snake movement → food
and growth → color + HUD → game over → smoke checks) and tick them off as you go.
Gameplay to implement
- A bordered play field drawn with
curses. - A snake that moves continuously and is steered with W, A, S, D (arrow keys as a fallback).
- q (or Q) and ESC quit the game at any moment.
- Food that spawns at a random empty cell; eating it grows the snake and increases the score.
- Game over when the snake hits a wall or itself; show a centered "GAME OVER — score N" screen and wait for a keypress to exit.
- Restore the terminal cleanly on exit (use
curses.wrapperso a crash never leaves the terminal garbled).
Make it flashy
- Color (guard with
curses.has_colors()): green snake, red food, yellow score bar, white borders — set upcurses.init_pairpairs once at start and fall back to plain text when colors are unsupported. - Score HUD: a top status line like
SCORE 7 · SPEED 3that updates live. - Speed ramp: every 3 pieces of food eaten, shorten the tick timeout a little so the game gets faster — cap it so it stays playable.
- Eat animation: a short, non-blocking flourish when the snake eats food — e.g. flash the snake's head or pulse the score in the HUD for a few ticks. It must not pause the game loop.
- Death animation: on game over, a brief sequence before the "GAME OVER" screen — e.g. flash the snake a few times or make it disintegrate tail-to-head. Keep it under ~a second so quitting never feels sluggish.
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 · 57 lines · 46 tokens per session scan A 77fe53abce07
demo-1-terminal-arcade is a skill published in the GitHub repository decodingai-magazine/building-a-coding-agent-from-scratch-course (387 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 752 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
pygame-core
Structure a pygame (pygame-ce) game in Python: the init/event/update/draw loop, delta-time movement, Surface/Rect blitting, keyboard/mouse input, and Sprite/Group management with collision. Use when building or debugging a pygame game — when the user mentions pygame, pygame-ce, the game loop, blit, Surface, Rect…
vibeue
Unreal Engine 5 development using the VibeUE Python API. Use when working in Unreal Engine — blueprints, state trees, materials, actors, landscapes, animation, niagara, widgets, sound, foliage, gameplay tags, enhanced input, skeletons, PCG (procedural content generation), and more. VibeUE is an extension of Unreal's…
telnyx-numbers-python
Search, order, and manage phone numbers by location, features, and coverage.
telnyx-ai-outbound-voice-python
End-to-end setup for making a Telnyx AI assistant call a phone number. Covers provisioning a phone number, creating a TeXML application, assigning the number, configuring telephony settings, whitelisting destination countries, and triggering outbound calls via scheduled events. Use this skill (not…
telnyx-stt-python
Transcribe audio to text via the OpenAI-compatible transcription endpoint. Supports multiple models, languages, and keyword biasing. Also lists available speech-to-text providers and service types.
telnyx-tts-python
Generate speech from text using Telnyx and third-party TTS providers (AWS, Azure, ElevenLabs, MiniMax, Resemble, Rime, xAI). Returns base64-encoded audio or a binary stream. Also lists available voices per provider.