Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Gauntlet Loop

Turn any plan, spec, or objective into a copy/paste system prompt that executes it through an orchestrator, an implementer, and a gauntlet of blind critics.

Gauntlet Loop is an agent skill for Claude Code, Codex, and 70+ other agents. Give it an objective, a markdown plan, or an HTML spec — it emits a fully optimized execution system prompt built on three separated roles:

Role Who Job
Orchestrator / Critic Claude Decomposes, delegates, adjudicates evidence. Never implements.
Implementer Codex Produces every artifact via block-structured delegation contracts.
Blind critics Fresh-context sub-agents Hostile auditors who never see the implementer's self-assessment. Loop until the evidence passes, not the claims.

The core principles: the agent that implements never grades its own work, a critic that watched a previous draft never grades the retry, and the bar must be real — concrete criteria and reference exemplars the critic compares against side by side, not "make it amazing."

Inspired by and extending Matt Shumer's Gauntlet Loop technique.

📖 Docs: nicholasspisak.github.io/gauntlet-loop

Install

Via the skills CLI:

npx skills add NicholasSpisak/gauntlet-loop

Install to specific agents, globally:

npx skills add NicholasSpisak/gauntlet-loop -g -a claude-code -a codex

Or use once without installing:

npx skills use NicholasSpisak/gauntlet-loop@gauntlet-loop | claude

Usage

/gauntlet-loop <objective>
/gauntlet-loop docs/plans/my-plan.md
/gauntlet-loop specs/feature.html

Input forms:

  • Inline objective — free text becomes the mission; acceptance criteria are derived and marked DERIVED for your confirmation.
  • Markdown file — treated as the source of truth; its checkboxes, gates, SLAs, and "never do" rules are extracted verbatim.
  • HTML file — content is extracted (headings, lists, tables, checklists); markup is ignored.

Output: one fenced code block containing the complete system prompt, ready to paste into a fresh session, plus up to three bullets flagging gaps (missing criteria, ambiguous gates, derived assumptions).

What the generated prompt contains

  1. Mission — the destination (never the implementation), bound to your document as the single source of truth.
  2. The bar — your document's own criteria plus concrete reference exemplars for side-by-side, blind comparison.
  3. Role split — a hard boundary: the orchestrator never implements.
  4. The loop — contract → implement → blind audit → iterate with fresh critics → adversarial second opinion → mark and log. No arbitrary iteration cap.
  5. Codex delegation contract — XML block structure tuned for GPT-5.4-class implementers (task, verification_loop, action_safety, …).
  6. Critic contract — the hostile-auditor prompt, bound to the bar; the work must win or tie against the reference.
  7. Fan-out map — smallest separately-judgeable pieces; gated-sequential vs. safely parallel.
  8. Progress ledger — a live workbench.md for non-intrusive human monitoring.
  9. Hard stops — human approval gates and fail-closed safety rules that outrank the loop. "Keep going until perfect" never self-approves a sign-off.
  10. Definition of done — every criterion critic-verified, a final smoothing pass over the integrated whole, every pending human gate listed.

Why this shape

Single-agent "do it perfectly and check your work" prompts fail two ways: the implementer grades its own homework, and iterative critics grade improvement instead of the bar. Gauntlet Loop enforces both separations structurally — blind critics, fresh instance per retry, evidence-only adjudication — and adds the piece most loop prompts miss: human gates that the loop cannot override.

Repository layout

skills/
  gauntlet-loop/
    SKILL.md                          # The skill
    references/
      prompt-template.md              # Canonical generated-prompt skeleton
      delegation-contract.md          # Codex XML block library
      critic-contract.md              # Blind hostile-audit contract
docs/                                 # GitHub Pages documentation

License

MIT © Nicholas Spisak

About

Turn any plan, spec, or objective into a copy/paste system prompt with orchestrator, implementer, and blind-critic roles. Agent skill for Claude Code, Codex + 70 more.

Resources

Stars

3 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors