guard-widget

The 2048 sliding-tile puzzle; it plays itself until you take the keys.

Ask a yes or no question and get an answer of doubtful reliability.

The most recent tool calls with how long each took and whether it failed.

Where a command lands outside this folder: the kube context, cloud profile, Terraform workspace or database it is aimed at, named in the permission dialog

What changed in the system prompt and the built-in tool descriptions Claude Code gives Claude since the version you last ran, with the before and after one command away

An aquarium with a fish for every running tool call and agent.

The Dropbox plugin for Claude connects your Dropbox files directly to Claude, so you can search, organize, save generated content, and create sharing links without switching tools. It respects your existing Dropbox permissions, and Claude only works with files you already have access to.

6 skills · 1 MCP server

The Dropbox plugin for Claude connects your Dropbox files directly to Claude, so you can search, organize, save generated content, and create sharing links without switching tools. It respects your existing Dropbox permissions, and Claude only works with files you already have access to.

6 skills · 1 MCP server

Roll Claude Code out to a team with guardrails you can check. Four deterministic stdlib scripts: a settings linter that reads shared, local, user and managed settings together (array merge, deny-ask-allow order) and blocks blanket shell allows, pre-approved destructive commands and committed credentials; an MCP and plugin inventory that blocks anything missing from your approved list or holding a literal secret, and flags unpinned or plain-http servers; a CLAUDE.md layering audit that resolves every layer and @import and flags broken imports, contradictions, secrets and resident size; and a privacy-safe adoption tracker that turns local session files into counts only and classifies the rollout as PILOT, SPREADING, EMBEDDED or STALLED. Ships cs-claude-code-rollout agent, /cs-claude-rollout and /cs-claude-settings-lint commands, 3 references, a baseline managed-settings policy and a four-phase rollout plan.

1 skill · 2 commands · 1 agent

Entry point for Internet Court and the agentic economy stack: natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, GenLayer dispute resolution, and the vendored protocol + connector skills it routes to.

96 skills

Multi-agent orchestration grounded in an LLM wiki. /dev-loop:orchestrate splits one goal into a dependency graph of parallel Claude Code sessions, each in its own worktree, and supervises them natively on Orca (a tracked Task + Dispatch per phase, pushed worker_done / question / escalation events instead of polling, stall detection; raw tmux fallback). Every plan decision must cite a page in a bundled best-practice wiki of 400+ pages across 10 domains, checked by machine gates and a fresh-context plan reviewer. Insights from your sessions are queued and turned into reviewed wiki PRs when you run /dev-loop:knowledge-flush (automatic flushing is opt-in and never bypasses permission checks).

9 skills · 11 agents · 1 MCP server · hooks

Generative UI design system for rendering interactive HTML/SVG widgets in Claude conversations.

1 skill