gauntlet-loop

gauntlet-loop is a skill for Claude Code, Codex, Cursor from emaraschio/cursor-commands. It costs 139 tokens per session (2,806 once invoked), scanned A, original, MIT.

Beat a real-world quality bar with a Gauntlet Loop: take a GOAL and a REAL-WORLD EQUIVALENT with an inspectable reference pack, decompose into independent parts, assign specialist builders, and gate each part behind a separate fresh-context critic. Pass only if better than the reference; otherwise return the largest…

Skill for Claude CodeCodexCursor

Install

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.

agentmods
npx agentmods add skills/emaraschio/cursor-commands/gauntlet-loop
Any agent
npx skills add emaraschio/cursor-commands --skill gauntlet-loop
Clone the repo
git clone --depth 1 https://github.com/emaraschio/cursor-commands

Made for: Claude Code, Codex, Cursor.

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.

agentmods badge for gauntlet-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/emaraschio/cursor-commands/gauntlet-loop.svg)](https://agentmods.dev/skills/emaraschio/cursor-commands/gauntlet-loop)
Your own site
<a href="https://agentmods.dev/skills/emaraschio/cursor-commands/gauntlet-loop"><img src="https://agentmods.dev/badge/skills/emaraschio/cursor-commands/gauntlet-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,806 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00139 $0.02806
Opus 5 $0.00069 $0.01403
Sonnet 5 $0.00028 $0.00561
Haiku 4.5 $0.00014 $0.00281

Measured today against content hash a06055908193, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gauntlet-loop 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 today.

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.

.cursor/skill-contracts/gauntlet-loop/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gauntlet loop

Role

You run a Gauntlet Loop: raise quality by competing against a real example, not against a vague "make it better". You decompose the GOAL, assign specialist builders, and let critics alone decide when each part passes. A part passes only when the critic judges the generated artifact better than the REAL-WORLD EQUIVALENT (the reference). Equal or worse is fail. Otherwise the critic returns the largest specific gap and the builder iterates. After all parts pass, an integration critic grades the whole artifact against the whole reference pack. Do not let builders evaluate their own work.

When to use

Use when the user invokes /gauntlet-loop, asks to beat a real-world equivalent, run a builder/critic gauntlet, or set a concrete quality bar via an excellent existing example. For a six-part Goal before autonomous work without a reference bar, use define-agent-goal. For post-build judgment autopsy, use decision-audit. For thinning instructions from a bare run, use instruction-ablation.

Gauntlet charter

Goal plus an inspectable reference pack. Decompose. Specialist builders. Fresh-context critics inspect and compare. Blind when possible. Pass only if better (equal fails). Else largest specific gap. Cap, stall, and budget. Integration critic on the whole. Pride gate on taste. Gap ledger for resume. Builders never grade themselves.

Workflow

Run phases in order.

Phase 0: Intake

  1. Require two fields:
    • GOAL: the finished result to produce
    • REAL-WORLD EQUIVALENT: name, URL, attachment, or description of an excellent existing example that sets the quality bar (also called the reference)
  2. Require an inspectable reference pack: files, screenshots, short clip, playable build, or repo path that a critic can open. A name alone is not a pack. The reference is the quality bar; the reference pack is what critics open. Assemble the pack at intake; critics receive only the pack (plus the unlabeled generated twin when blind).
  3. If GOAL, REAL-WORLD EQUIVALENT, or a usable reference pack is missing, ask one focused question per gap. Do not invent the reference or a vague substitute bar.
  4. Optionally accept:
    • iteration cap (default 5 rounds per part)
    • BUDGET: total rounds across all parts and/or wall-clock limit (default: none beyond the per-part cap)
    • constraints, scope limits
  5. If the reference is named but inaccessible (dead link, missing attachment, no inspectable artifact) or a pack cannot be assembled, stop and ask how to obtain it. Do not invent a substitute bar or proceed on memory of a famous product alone.
  6. If the work is production-destructive and constraints lack explicit consent for that blast radius, stop and ask before building.
  7. On resume of a prior gauntlet, read the existing gap ledger first. Do not retry a gap already marked stalled without a changed approach.

Read the full file on GitHub · 164 lines

Files

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.

Changes

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.

  1. today First seen · 164 lines · 139 tokens per session scan A a06055908193

Subscribe to this mod's changes

gauntlet-loop is a skill published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 27d ago), licensed MIT. It adds 139 tokens to every session and 2,806 once invoked, about $0.0007 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 2026-09-03.

Related

Other skills, from other repositories

grok-build-supervisor

Initialize the persistent local proxy, then immediately ensure a visible Grok Build TUI for the current workspace when /grokexecute on activates, and continuously supervise that coding-agent session through a user-level Supervisor daemon as the user sends work, waits for completion, reconnects from another host task…

Vanyangyang/cursor-bridge · 103 tokens

cursor-delegate

Delegate bounded light-to-medium implementation, investigation, documentation, configuration, testing, and tooling work to Cursor Bridge after the primary agent owns direction and risk boundaries. Also use when the user explicitly asks to create, keep, continue, inspect, or close the same Cursor execution session…

Vanyangyang/cursor-bridge · 151 tokens

grok-executor-mode

Task-local execution policy applied to ordinary user tasks only after an exact /grokexecute on; the host agent then plans, supervises, corrects, and verifies while all implementation and workspace-mutating execution goes through Grok Build Supervisor. Never activate or deactivate from ordinary requests, task text…

Vanyangyang/cursor-bridge · 73 tokens

deep-research

Conducts multi-step deep research on any topic using iterative search, reflection, and synthesis. Use when the user asks to research, investigate, survey, compare, analyze, deep-dive, or explore a topic in depth. Covers web research, codebase analysis, documentation review, mixed-source investigation, and M3…

madebyaris/advance-minimax-m3-cursor-rules · 72 tokens

incident-triage-harness

Production-style incident triage workflow for logs, metrics, code, safe mitigations, and M3 multimodal visual evidence (screenshots, screen recordings). Use when debugging alerts, regressions, outages, or suspicious runtime behavior.

madebyaris/advance-minimax-m3-cursor-rules · 53 tokens

web-design

Build distinctive, production-grade frontend interfaces with high design quality. Use when asked to build websites, landing pages, dashboards, web apps, or any web UI that should look polished and modern. Generates creative, polished code that avoids generic AI aesthetics. Includes Yesterday corporate identity…

Yesterday-AI/skills · 64 tokens