caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Task graphs with loops and human gates for AI-governed engineering (idea to PR), the council, P10, Safety Car and Cabinet skills, and a dependency-free MCP server. No API key needed.
Plugin toto-wolff from marketplace toto-wolff in ray-aqno/Toto-Wolff. Commands read from the repo's manifest — 28 days ago.
This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.
drsDrag Reduction System — ambient PreToolUse tripwire that fires deterministically on boundary violations. Not a slash command. Hooks into every tool call automatically.
graph-runDrive a toto-wolff task graph run step by step (the built-in idea-to-pr graph, or a project graph in .toto/graphs) with the graph_* MCP tools. Asks the user at every human gate and choice. Use for "run idea-to-pr on <idea>", "start a graph run", "resume run <runId>", or "/graph-run".
karpathyExecution-layer quality rules for implementation work. Active after a P10 plan reaches status: approved. Governs how code is written, not what is built.
linear-syncSync an approved toto-wolff P10 plan into a Linear issue through a connected Linear MCP connector. Use only when the user explicitly runs `/linear-sync <plan-path> --team <name> --project <name>`; never run it automatically or as a side effect of a /p10 approval.
llm-councilConvene a tiered LLM council to deliberate on engineering decisions, architecture choices, refactor strategies, PR reviews, prioritization calls, or any problem with meaningful trade-offs. Integrates with gstack's role-driven workflow and Claude Code subagents. Trigger on: "council this", "what shou
p10-bridgeApply NASA's Power of 10 safety rules as a pre-execution planning contract for any engineering task. Use this skill before writing or modifying code whenever a task has been defined (via gstack, /council ruling, or direct issue). The skill researches the codebase, drafts a P10-compliant implementati
safety-carAdversarial stress test of an approved P10 plan. Fires after Opus approval, before any file is touched. One Sonnet agent with one job — find how this plan fails.
the-cabinetThe final voice before release. Convenes three equal-seated luminaries — Garry Tan, Richard Feynman, Andrej Karpathy — to judge release readiness. Each seat returns an independent SHIP / CONDITIONAL / BLOCK verdict; any seat can veto a release by naming a release-critical defect. Trigger on "/cabine
toto-wolffruns: node ${CLAUDE_PLUGIN_ROOT}/server/index.mts --vault ${user_config.vault_path}
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
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.