Agent skill

Gauntlet Loop

by duolahypercho in duolahypercho/gauntlet-loop

GAME skill. An agent skill from duolahypercho/gauntlet-loop.

MITAuto-check passedMedia & Creative

Install Gauntlet Loop

skills CLI
$ npx skills add duolahypercho/gauntlet-loop --skill gauntlet-loop -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install duolahypercho/gauntlet-loop gauntlet-loop --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/duolahypercho/gauntlet-loop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/gauntlet-loop .claude/skills/gauntlet-loop && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gauntlet-loop
GitHub stars
163
Token cost
~689 tokens
SKILL.md length
281 words
Files
7
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

GAME skill. An agent skill from duolahypercho/gauntlet-loop.

  • Works in 4 steps: Read AGENTS.md — the prompt + game… → Read the harness overlay for loop verbs… → Infer nouns from $ARGUMENTS / the… → …
  • One-prompt game build
  • SKILL.md covers Art for the game (not instead… and Do not
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Gauntlet Loop is an agent skill from duolahypercho/gauntlet-loop. GAME skill. Run Matt Shumer's aim prompt to build a game against a named reference (COD, Hades, Brotato, …) — fill three paragraphs, execute, fan-out + harsh critic + blind A/B until the human stops you. Pure prompt; no harness. Art: image gen for 2D/textures, Blender MCP for 3D meshes — both feed the game. Claude (/gauntlet-loop, /loop) and Codex ($gauntlet-loop, /goal). Use for Gauntlet Loop, aim prompt, one-prompt game build, COD-style loop.

Its SKILL.md is about 690 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files (for example `AGENTS.md`, `ASSETS.md` and `BLENDER_MCP.md`).

It sits in Media & Creative, covering Image generation. It works with Blender and Model Context Protocol. The repository describes itself as: Gauntlet Loop — aim-prompt skill for Claude Code and Codex. Fan-out builders, harsh separate critic, blind A/B against an unreachable reference. You are the brake. The licence is MIT.

When your agent uses it

  • One-prompt game build
  • Tasks that involve Image generation

Example prompts

  • “/gauntlet-loop”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Read AGENTS.md — the prompt + game defaults + what not to invent.
  2. Read the harness overlay for loop verbs only
  3. Infer nouns from $ARGUMENTS / the message. Default domain = game. One question max if THING is missing.
  4. Fill → execute on the game → keep going until the human stops you.

What it can do on your machine

Read from SKILL.md and the folder at commit b63fbb6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gauntlet Loop loads about 689 tokens when it runs. Until then it costs about 116 tokens; SKILL.md has 281 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~116
When it runs · the whole SKILL.md, loaded when a task matches
~689

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from duolahypercho/gauntlet-loop at commit b63fbb6, republished under its MIT licence (© duolahypercho). 281 words, ~689 tokens.

Download SKILL.mdSave it as .claude/skills/gauntlet-loop/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
gauntlet-loop
description
GAME skill. Run Matt Shumer's aim prompt to build a game against a named reference (COD, Hades, Brotato, …) — fill three paragraphs, execute, fan-out + harsh critic + blind A/B until the human stops you. Pure prompt; no harness. Art: image gen for 2D/textures, Blender MCP for 3D meshes — both feed the game. Claude (/gauntlet-loop, /loop) and Codex ($gauntlet-loop, /goal). Use for Gauntlet Loop, aim prompt, one-prompt game build, COD-style loop.
argument-hint
[game to build] [optional: against REFERENCE] [optional: in STACK]

Gauntlet Loop

This is a game skill. Pure prompt. No functions.

On invoke you are building a game to the level of a named reference game. Fill the three-paragraph aim prompt, then run it. Do not paste it for the user. Do not build a capture suite, state machine, or scoring framework around it. The prompt is the method.

  1. Read AGENTS.md — the prompt + game defaults + what not to invent.
  2. Read the harness overlay for loop verbs only:
  3. Infer nouns from $ARGUMENTS / the message. Default domain = game. One question max if THING is missing.
  4. Fill → execute on the game → keep going until the human stops you.
text
/gauntlet-loop a COD-style FPS in ThreeJS
/gauntlet-loop Hades-like roguelike in Godot
/gauntlet-loop Brotato-like arena survivor in Godot

Art for the game (not instead of the game)

NeedToolDoc
Sprites, textures, UI pixels, conceptsImage genASSETS.md
2D hero/monsters (Brotato-like)Image gen sprite factory (style lock → hero → batch → import)ASSETS.md
Real meshes, GLB/FBX, 3D props/weaponsBlender MCPBLENDER_MCP.md + ASSETS.md

Critic grades in-game frames vs the real reference game. Art tools only close asset gaps — then wire into the playable build. For 2D sprite games, characters/monsters are image-gen sprites with one locked art language — not Blender, not procedural ovals.

Do not

  • Treat this as a generic site/deck skill — games first
  • Dump the prompt and stop — you run it
  • Invent tools, harnesses, contracts, or round machinery
  • Soften the critic / lower the reference / invent a stop condition
  • End after one cycle and ask whether to continue
  • Mix harness verbs (/loop on Codex, /goal on Claude, ultracode on Codex)
  • Lag the game out with capture farms / headless engine spam — the game stays playable
  • Replace the game loop with endless image-gen or Blender-only rounds

Fills: examples.md

© duolahypercho, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files in skills/gauntlet-loop of duolahypercho/gauntlet-loop.

  • SKILL.md
  • AGENTS.md
  • ASSETS.md
  • BLENDER_MCP.md
  • CLAUDE.md
  • CODEX.md
  • examples.md

Open the folder on GitHubat commit b63fbb6

Compare with similar skills

Gauntlet Loop next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gauntlet Loop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gauntlet Loop this skillduolahypercho/gauntlet-loop163—~689Automated safety check: PassMIT
Cullglebis/claude-skills389—~1.9kAutomated safety check: PassMIT
ComfyUI Local DriverSlavaSexton/ComfyUI-Agent-Kit105—~12kAutomated safety check: PassApache-2.0
Md2wechatgeekjourneyx/md2wechat-skill3.7k—~3.8kAutomated safety check: PassCustom licence
Sprite Genaldegad/sprite-gen2.6k—~4.5kAutomated safety check: PassApache-2.0
SEO Image GeneratorAgriciDaniel/claude-seo18k2 repos~2.1kAutomated safety check: PassMIT

Similar skills

  • Cull

    glebis/claude-skills

    This skill should be used when the user wants to view, review, rate, organize, search, or export images / AI-art generations with the Cull app.

    389 GitHub stars~1.9k tokensUpdated 12 days ago
    Media & CreativeAuto-check passed
  • ComfyUI Local Driver

    SlavaSexton/ComfyUI-Agent-Kit

    Drives a local ComfyUI install over its HTTP API to generate and edit images, video and audio, with per-model prompt recipes and workflow guidance.

    105 GitHub stars~12k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Md2wechat

    geekjourneyx/md2wechat-skill

    Convert Markdown to WeChat Official Account HTML. An agent skill from geekjourneyx/md2wechat-skill.

    3.7k GitHub stars~3.8k tokensUpdated 14 days ago
    Media & CreativeAuto-check passed
  • Sprite Gen

    aldegad/sprite-gen

    Generates images and game sprites through GPT or Grok with guided provider choices, separate saved defaults, automatic cleanup and optional curation.

    2.6k GitHub stars~4.5k tokensUpdated yesterday
    Game DevelopmentAuto-check passed
  • SEO Image Generator

    AgriciDaniel/claude-seo

    Generates Open Graph previews, blog hero images, product photos and infographics for SEO use through Gemini image tools and the banana extension.

    18k GitHub starsUsed in 2 repos~2.1k tokens
    Media & CreativeAuto-check passed
  • Gemini Skill

    WJZ-P/gemini-skill

    通过 Gemini 官网(gemini.google.com)执行生图、对话等操作。用户提到"生图/画图/绘图/nano banana/nanobanana/生成图片"等关键词时触发。操作方式分三级优先级:首选 MCP 工具 → 次选 Skill 脚本 → 最次连接 Skill 浏览器手动操作(需用户授权)。禁止自行启动外部浏览器访问 Gemini。

    832 GitHub stars~1.1k tokensUpdated 20 days ago
    Agent WorkflowsAuto-check passed

Questions about Gauntlet Loop

What does Gauntlet Loop do?

GAME skill. An agent skill from duolahypercho/gauntlet-loop. Gauntlet Loop is an agent skill from duolahypercho/gauntlet-loop. GAME skill.

When should I use Gauntlet Loop?

Gauntlet Loop fits situations like: one-prompt game build; tasks that involve Image generation.

How do I install Gauntlet Loop in Claude Code?

Run `npx skills add duolahypercho/gauntlet-loop --skill gauntlet-loop -a claude-code`. Or copy the skill folder (skills/gauntlet-loop in duolahypercho/gauntlet-loop) into .claude/skills/gauntlet-loop in your project. Claude Code loads it when a task matches its description.

How do I install Gauntlet Loop in Codex?

Run `npx skills add duolahypercho/gauntlet-loop --skill gauntlet-loop -a codex`. Or copy the skill folder (skills/gauntlet-loop in duolahypercho/gauntlet-loop) into .agents/skills/gauntlet-loop in your project. Codex loads it when a task matches its description.

Can I use Gauntlet Loop in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add duolahypercho/gauntlet-loop --skill gauntlet-loop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gauntlet-loop, .gemini/skills/gauntlet-loop, .github/skills/gauntlet-loop and .opencode/skills/gauntlet-loop in your project.

What does Gauntlet Loop need to run?

SKILL.md names no scripts, command-line tools or credentials: Gauntlet Loop is instructions for the agent only.

Does Gauntlet Loop access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Gauntlet Loop safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Gauntlet Loop use?

Gauntlet Loop is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gauntlet Loop use?

About 689 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gauntlet Loop?

Skills that share tags, products or a category with Gauntlet Loop: Cull (glebis/claude-skills, 389 stars), ComfyUI Local Driver (SlavaSexton/ComfyUI-Agent-Kit, 105 stars), Md2wechat (geekjourneyx/md2wechat-skill, 3.7k stars) and Sprite Gen (aldegad/sprite-gen, 2.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gauntlet Loop?

duolahypercho (a GitHub user) maintains it in duolahypercho/gauntlet-loop, which has 163 GitHub stars. The repository was last updated on July 28, 2026.

Source: duolahypercho/gauntlet-loop on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.