Gauntlet Loop harness — give an agent a hard external bar it cannot talk its way around, let it split the work, and never let the builder grade itself. Mechanically-blind A/B critics, a five-check bar-soundness gate, receipted verdicts, and a live progress board. Bar recipes for agentic capabilities, reinforcement learning, and general coding.
Plugin gauntlet from marketplace kraken in KrakenNet/kraken-plugins. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
gauntlet-loopUse when running a Gauntlet Loop — driving work to a high quality bar by splitting it into independently judgeable pieces, building each with one agent, and judging each with a separate blind critic against a concrete external reference, looping until the reference stops winning. Covers agentic capa
/gauntlet:barFind and validate the quality bar for the current Gauntlet Loop. Dispatches bar-scout, runs the five soundness checks, writes .gauntlet/bar.md. The loop cannot stage a trial until this passes.
/gauntlet:newStart a Gauntlet Loop — capture the goal, pick the domain, write .gauntlet/charter.md, then hand off to /gauntlet:bar.
/gauntlet:runRun the Gauntlet Loop — lead decomposes the goal, each piece gets a builder and a separate blind critic, losing rounds go back to the builder, and the loop keeps going until you stop it.
/gauntlet:statusShow Gauntlet Loop state — per-piece round history, win/loss against the bar, open gaps, trials awaiting a verdict. Renders the live board.
bar-scoutFinds and validates the quality bar for a Gauntlet Loop. Proposes concrete external references, runs the five soundness checks, names the cheapest way to game each, and writes .gauntlet/bar.md. Dispatch before any loop starts, or when a bar has gone soft.
builderGauntlet Loop builder. Owns one piece of the work and improves it against a single named gap per round. Never judges its own output. Dispatched by gauntlet:lead once per piece per round.
criticGauntlet Loop critic. Judges one blind A/B trial — inspects two artifacts without knowing which is ours, picks the better, names the single largest gap. Fresh context every trial. Dispatched by gauntlet:lead once per trial.
leadGauntlet Loop lead. Owns decomposition, wave scheduling, staging blind trials, revealing verdicts, and the live board. Never builds and never judges. Dispatch when a /gauntlet:run starts or resumes.
smootherEnd-of-wave coherence pass for a Gauntlet Loop. Inspects the whole artifact after many builders changed separate pieces, reconciles conflicts and inconsistencies, does not redesign. Dispatched by gauntlet:lead between waves.
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/key-guard.py
Guided creation and management of Railyard platform entities (agents, governors, tools, workflows, credentials, knowledge graph, memories, chat sessions, knowledge bases, integrations, inbound sources, LLM models, ML stack, pipelines, skills, chatbots, budgets, alerts, compliance, dashboards, webhooks) via REST API with iterative build-test-fix verification.
3 skills · 26 commands · 10 agents
Ultimate AI software team — 17-stage spec-anchored pipeline with dual interrogation (PM + design), parallel research, locked tests, adversarial Ralph Loop, anti-cheat gate, inter-stage review, spec GraphRAG, Reflexion lessons, failure recipes, cheap-model triage, and Phase 3 CI/CD ensemble reviewers.
2 skills · 8 commands · 17 agents · hooks
Author + operate Stargraph — graphs, skills, nodes, tools, triggers, Bosun rule packs, markdown SKILL.md skills, directory-based plugins; run/replay/counterfactual against stargraph serve, drive HITL, inspect checkpoints.
2 skills · 18 commands · 8 agents
Kraken Knowledge Base lifecycle management — works with railyard, fathom, nautilus, stargraph. Create, update, audit, lint, and manage KB articles with automatic staleness detection and KB-first development enforcement.
2 skills · 11 commands · 5 agents
Author and operate Fathom CLIPS rule packs — scaffold packs, templates, and rules; validate/test/bench locally; evaluate, hot-reload, and verify artifacts against a running engine.
2 skills · 10 commands · 4 agents · 1 MCP server
Author and operate Nautilus brokers — scaffold sources, adapters, and rule packs; drive request/sources/caps APIs; verify attestations and tail audit logs.
2 skills · 10 commands · 4 agents · 1 MCP server
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Use Alibaba Open Code Review from local Codex.
2 skills
Claude Code skill for creating and presenting Slidev slidedecks
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.