cache-tax

Themeable rendering for replies: tables, code, Mermaid diagrams and charts with copy buttons. Adds ~630 tokens of formatting hints per prompt by default. Reviewed: Caution.

4 skills

One live line above the prompt per running subagent: time, tool count and what it's doing. /radar shows every agent and its messages. Reviewed: Recommend.

Your context window as a stacked bar above the prompt, a color per category, with token counts and the compaction point. Reviewed: Recommend.

A resident product team in Claude Code, run from its own pane with buttons and fields, no command needed: a PM splits your PRD into features and acceptance criteria, QA writes a test case for each, a UI/UX designer writes a design for each feature that you approve on one page with the PRD draft and the roles' questions, a tech lead breaks the criteria into tasks and reviews the code, a full-stack agent builds the tasks on crew's own git branch and worktree, and crew runs your test command and maps the results to the test cases. Each role runs on Claude or Codex, from a floor you set, stepping up with how hard the work is. Gaps and product questions come back to you in the pane. A heartbeat looks after the work every five minutes, a restart asks before going on, and token reminders go to Claude, which acts on usage only as you allow. The board is held to the PRD as it stands. Keeps its memory in the repo. Made here. Work in progress.

An IDE-style file tree pane with git status that highlights files as Claude reads or edits them. Runs read-only git, find and du plus small helpers. Reviewed: Recommend.

A live agent dashboard pane: model vitals, every permission check, subagent cards and a session log. Observes only. Reviewed: Recommend.

Security default for organizations: seated outermost, it keeps the organization's classic hooks, prompt content, settings, tool policy and pinned environment out of reach of the plugins a person installs, and adds no policy of its own; one managed option, allowManagedModsOnly, limits mods to the organization's.

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.

1 skill

Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform real-world tasks: listing resources, validating deployments, diagnosing infrastructure issues, and optimizing costs across 50+ Azure services.

44 skills · 1 MCP server

Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).

1 skill · hooks