New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Gauntlet Loop

by robonuggets in robonuggets/gauntlet-loop

Turns any goal into one short, paste-ready "gauntlet loop" prompt - a prompt that makes an agent set a concrete quality bar, split the work into small judgeable pieces, run a builder and a separate…

CC-BY-4.0Auto-check passed

Install Gauntlet Loop

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

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

GitHub CLI
$ gh skill install robonuggets/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/robonuggets/gauntlet-loop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/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
1k
Token cost
~2k tokens
SKILL.md length
814 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
CC-BY-4.0

At a glance

Turns any goal into one short, paste-ready "gauntlet loop" prompt - a prompt that makes an agent set a concrete quality bar, split the work into small judgeable pieces, run a builder and a separate…

  • Works in 4 steps: Read the goal. One line restatement in… → Set the bar. If the user supplied a… → Write the prompt. One block,… → …
  • Make a gauntlet prompt
  • SKILL.md covers Flow, The bar is the whole trick, Prompt template and Length and voice, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Gauntlet Loop is an agent skill from robonuggets/gauntlet-loop. Turns any goal into one short, paste-ready "gauntlet loop" prompt - a prompt that makes an agent set a concrete quality bar, split the work into small judgeable pieces, run a builder and a separate harsh critic on each, compare blind against the bar, and loop until it wins. Works for builds, writing, code, research, or design. Triggers on "/gauntlet-loop", "gauntlet loop", "gauntlet this", "make a gauntlet prompt", "loop until it beats X".

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Turn any goal into a short prompt that makes your agent set a real quality bar, run builder and critic pairs, compare blind, and loop until it wins. The licence is CC-BY-4.0.

When your agent uses it

  • Make a gauntlet prompt
  • Loop until it beats X

Example prompts

  • “gauntlet loop”
  • “/gauntlet-loop”
  • “gauntlet this”
  • “/gauntlet-loop”

Workflow steps

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

  1. Read the goal. One line restatement in your head, not on screen.
  2. Set the bar. If the user supplied a reference, use it. If not, offer 2 or 3 candidate bars, one line each, and stop. Wait for their pick…
  3. Write the prompt. One block, paste-ready, no preamble, no headings inside it, no narration after it.
  4. Offer to run it. One flat line under the prompt: "I can run this here." Not a question.

What it can do on your machine

Read from SKILL.md and the folder at commit 9b1975a. 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 2k tokens when it runs. Until then it costs about 114 tokens; SKILL.md has 814 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~114
When it runs · the whole SKILL.md, loaded when a task matches
~2k

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 robonuggets/gauntlet-loop at commit 9b1975a, republished under its CC-BY-4.0 licence (© robonuggets). 814 words, ~2,038 tokens.

Download SKILL.mdSave it as .claude/skills/gauntlet-loop/SKILL.md (or your agent's skills folder).
name
gauntlet-loop
description
Turns any goal into one short, paste-ready "gauntlet loop" prompt - a prompt that makes an agent set a concrete quality bar, split the work into small judgeable pieces, run a builder and a separate harsh critic on each, compare blind against the bar, and loop until it wins. Works for builds, writing, code, research, or design. Triggers on "/gauntlet-loop", "gauntlet loop", "gauntlet this", "make a gauntlet prompt", "loop until it beats X".

Gauntlet Loop

The user gives a goal. You give back ONE short prompt they can paste into a fresh agent session.

You are not doing the work. You are writing the prompt that makes another agent grind on the work until it beats a real reference.

Flow

  1. Read the goal. One line restatement in your head, not on screen.
  2. Set the bar. If the user supplied a reference, use it. If not, offer 2 or 3 candidate bars, one line each, and stop. Wait for their pick. Do not write the prompt yet.
  3. Write the prompt. One block, paste-ready, no preamble, no headings inside it, no narration after it.
  4. Offer to run it. One flat line under the prompt: "I can run this here." Not a question.

If they say run it, you become the lead agent and follow the prompt you just wrote.

The bar is the whole trick

Everything else in a gauntlet loop is scaffolding. The loop only produces quality if the thing it compares against is real.

A bar has to pass three tests:

  • Named. A specific thing, not a category. "Stripe's pricing page" works. "Award-winning SaaS sites" does not.
  • Fetchable. The critic can actually get it - screenshot the live page, read the published piece, run the binary, open the repo, watch the footage. If the agent cannot obtain it, it will hallucinate the comparison.
  • Comparable. Both can sit side by side and a judge can pick one. If you cannot imagine the A/B, it is not a bar.

Bars by goal type:

GoalBar that works
Website, app, UIThe live site of a specific best-in-class product, screenshotted at the same viewport
Game, 3D, visualReal footage or screenshots from a named shipped title
WritingA specific published piece by a named author or publication, same length and format
Code, toolingA named repo's implementation, plus its benchmark or test suite as the measurable half
Research, analysisA named analyst report or a paper's methods section, judged on rigour and coverage
Deck, doc, deliverableA real artifact from a firm known for it, same page count

When you propose bars, prefer the hardest one the agent can genuinely reach. A bar that is too easy makes the loop exit on round one.

If the goal has a measurable half (load time, token cost, benchmark score, word count, pass rate), name it alongside the reference. Taste plus a number beats taste alone.

Prompt template

Adapt the wording every time. Fill the brackets, keep it short, keep the last line.

Build [GOAL].

The bar is [BAR]. Get the real thing first and compare against it directly, not against a description of it.

Break this into the smallest pieces that can be improved and judged on their own. For each piece, fan out a builder and a separate critic with fresh context. The critic inspects the actual output, puts it next to the bar blind with the labels stripped, says which one is better, and names the single biggest remaining gap. Then it goes back to the builder.

The critic should be a harsh critic. Praise is not useful. If ours does not win, it keeps going.

/loop on each piece until the critic picks ours blind. Do not stop before that.

Keep a live progress page updating as the work evolves so I can watch it.

Fan out subagents and ultracode.

Rules for what you fill in:

  • Bake the bar in as a concrete, fetchable thing. URL, product name, repo, title.
  • Add a budget or cost ceiling line only if the user named one. No default cap.
  • Add tool names only if the goal needs them (image or video generation, a browser, a deploy target).
  • Everything else stays out. No architecture, no file layout, no decomposition, no round count, no stack choice unless the user demanded it. The agent decides those, and it decides better than a spec written before the work started.
Show full SKILL.md (295 more words)Show less

Length and voice

Short. Around 120 to 180 words. If the prompt needs a heading to stay readable, it is too long.

Plain sentences. No bullet lists inside the prompt. It should read like someone telling an agent what perfect looks like and refusing to accept less.

Portability

/loop and ultracode are Claude Code features. /loop reruns the prompt on an interval or lets the model pace itself. ultracode opts the turn into multi-agent orchestration.

For any other agent, swap the last two lines for: "Keep looping until the critic picks ours. Run the builders and critics as parallel subagents." The structure carries over unchanged.

Two filled examples

Visual goal. User: "landing page for my running brand, athletic, green and dark, has to feel alive."

Bars offered: A) Nike's current running campaign page B) On Running's homepage C) Gymshark's product landing page. User picks A.

Build a landing page for a running brand. Athletic, peak performance, green and dark, energetic, aimed at a young healthy audience. It needs to be interactive and visually unmistakable.

The bar is Nike's current running campaign page. Screenshot it at desktop and mobile and compare against those directly, not against a description of them.

Break this into the smallest pieces that can be improved and judged on their own - hero, motion, type, colour, imagery, interaction, mobile. For each piece, fan out a builder and a separate critic with fresh context. The critic opens the real page in a browser, puts our screenshot next to Nike's blind with the labels stripped, says which is better, and names the single biggest remaining gap. Then it goes back to the builder.

The critic should be a harsh critic. Praise is not useful. If ours does not win, it keeps going.

/loop on each piece until the critic picks ours blind. Do not stop before that.

Keep a live progress page updating as the work evolves so I can watch it.

Fan out subagents and ultracode.

Non-visual goal. User: "a 2000-word explainer on vector databases for non-engineers."

Bars offered: A) a specific Stripe engineering blog explainer B) a named Julia Evans post C) the Wikipedia article plus a comprehension test. User picks B.

Write a 2000-word explainer on vector databases for readers who are smart but not engineers.

The bar is Julia Evans' writing on hard technical topics. Pull three of her actual posts and compare against them directly, not against a description of her style.

Break this into the smallest pieces that can be judged on their own - the opening, each explanation, the diagrams, the analogies, the ending. For each piece, fan out a writer and a separate critic with fresh context. The critic reads ours and hers blind with the bylines stripped, says which one a non-engineer would understand faster, and names the single biggest remaining gap. Then it goes back to the writer.

The critic should be a harsh critic. Praise is not useful. If ours does not win, it keeps going.

/loop on each piece until the critic picks ours blind. Do not stop before that.

Keep a live progress page updating as the work evolves so I can watch it.

Fan out subagents and ultracode.

What breaks a gauntlet loop

  • A vague bar. The critic invents a comparison and approves everything. Most common failure by far.
  • The builder judging its own work. The critic must be a separate agent with fresh context. It should not know how hard the builder tried.
  • A soft critic. Say "harsh" in the prompt and give it a binary job: which one is better, A or B. Scores out of 10 drift upward every round.
  • Named exit after N rounds. The exit is winning the comparison, or the user stopping the run. Never a round count.
  • Over-specifying. Every extra instruction is one fewer decision the agent makes with its own judgment. Minimal wins.

© robonuggets, CC-BY-4.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/gauntlet-loop of robonuggets/gauntlet-loop.

Open the folder on GitHubat commit 9b1975a

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 skillrobonuggets/gauntlet-loop1k—~2kAutomated safety check: PassCC-BY-4.0
Goalscodewhale-hq/Codewhale41k—~273Automated safety check: PassMIT
Shortsickn33/agentic-awesome-skills47k1 repos~281Automated safety check: PassMIT
Fable Goalalirezarezvani/claude-skills28k—~2.4kAutomated safety check: PassMIT
Agent Goal Plannerruvnet/ruflo74k3 repos~842Automated safety check: PassMIT
Goal Planruvnet/ruflo74k—~807Automated safety check: NotesMIT

Similar skills

  • Goals

    codewhale-hq/Codewhale

    Set, review, and update the user's goals. An agent skill from codewhale-hq/Codewhale.

    41k GitHub stars~273 tokensUpdated today
    Auto-check passed

  • Short

    sickn33/agentic-awesome-skills

    Rewrite the previous response more briefly while preserving the substance.

    47k GitHub starsUsed in 1 repo~281 tokens
    Auto-check passed

  • Fable Goal

    alirezarezvani/claude-skills

    Convert a rambling description of a desired outcome into one polished, autonomous /goal prompt ready to paste into a fresh session.

    28k GitHub stars~2.4k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Agent Goal Planner

    ruvnet/ruflo

    Agent skill for goal-planner - invoke with $agent-goal-planner

    74k GitHub starsUsed in 3 repos~842 tokens
    Auto-check passed

  • Goal Plan

    ruvnet/ruflo

    Create and execute Goal-Oriented Action Plans (GOAP) with precondition analysis, cost optimization, and adaptive replanning

    74k GitHub stars~807 tokensUpdated today
    Auto-check: notes

  • Paste Inputs

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Allow pasting into form inputs.

    74k GitHub stars~443 tokensUpdated 2 days ago
    Frontend & DesignAuto-check passed

Questions about Gauntlet Loop

What does Gauntlet Loop do?

Turns any goal into one short, paste-ready "gauntlet loop" prompt - a prompt that makes an agent set a concrete quality bar, split the work into small judgeable pieces, run a builder and a separate…. Gauntlet Loop is an agent skill from robonuggets/gauntlet-loop. Turns any goal into one short, paste-ready "gauntlet loop" prompt - a prompt that makes an agent set a concrete quality bar, split the work into small judgeable pieces, run a builder and a separate harsh critic on each, compare blind against the bar, and loop until it wins.

When should I use Gauntlet Loop?

Gauntlet Loop fits situations like: make a gauntlet prompt; loop until it beats X.

How do I install Gauntlet Loop in Claude Code?

Run `npx skills add robonuggets/gauntlet-loop --skill gauntlet-loop -a claude-code`. Or copy the skill folder (.claude/skills/gauntlet-loop in robonuggets/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 robonuggets/gauntlet-loop --skill gauntlet-loop -a codex`. Or copy the skill folder (.claude/skills/gauntlet-loop in robonuggets/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 robonuggets/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 CC-BY-4.0 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 2k tokens (SKILL.md is roughly 8.2k 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: Goals (codewhale-hq/Codewhale, 41k stars), Short (sickn33/agentic-awesome-skills, 47k stars), Fable Goal (alirezarezvani/claude-skills, 28k stars) and Agent Goal Planner (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gauntlet Loop?

robonuggets (a GitHub user) maintains it in robonuggets/gauntlet-loop, which has 1,044 GitHub stars. The repository was last updated on August 5, 2026.

Source: robonuggets/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.