Development plugins

Reference for vim.lsp, vim.lsp.buf, vim.lsp.util, vim.lsp.codelens, vim.lsp.semantic_tokens, and the LSP protocol APIs in Neovim Lua. Use when wiring language-server features (hover, definitions, references, code actions, formatting, completion, inlay hints).

Interactive debugging, developer experience optimization, and smart debugging workflows

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

Frontend UI development and mobile application implementation across platforms

Multi-agent code creation workflow — 6-phase pipeline with parallel subagents for exploration, architecture, implementation, and review

[TODO: brief plugin description]

[TODO: brief plugin description]

No description.

No description.

No description.

Intempt CLI + MCP server for Claude Code

cc-guides rendered-artifact guard — a capt-hook pack that blocks direct edits to cc-guides-rendered artifacts, steering to the fragments + `cc-guides render` flow.

Reference skill for Manim Community Edition (ManimCE) - installation, core concepts, CLI/config, TeX, and a cookbook of recipes.

A line above the prompt for each pull request Claude opens, merges by number, or is asked to watch, showing its GitHub workflows with a progress bar, then ready to merge, the failing job, or what blocks it, and telling Claude the same without being asked.

Works in a repository itos manages: titles each itos ID in Claude's replies.

Run Claude Code Workflow agents on GPT through the pi coding agent while Claude coordinates.

FlightDeck: a Claude Code agentic accelerator.

TypeScript/JavaScript language server that picks tsc --lsp (TS 7+) or typescript-language-server (TS 6 and earlier) per project

A Stop gate runs your test command after every turn that changed files and sends Claude back on failure; existing test files are locked.

A development verification board: shows which tests, builds and type checks really ran, how they ended, and whether the result still matches your code.

Jev (hosted) or Kev (local) picks the model for every subagent; live roster, decision bars, agent graph and context-exchange band; Codex, OpenCode and OpenRouter as external executors

Enforces git identity, attribution and branch-naming rules on Bash calls

Stops Claude adding banner, multi-line, long or narrating code comments

Hält riskante Befehle an (rm -rf, git reset --hard, Force-Push, Migrationen) und zeigt vorher, was weg wäre.

Spielt jede Änderung des letzten Turns Schritt für Schritt ab, auch Änderungen per Shell-Befehl.

Stoppt eine teure Nachricht an einen kalten Prompt-Cache einmal und zeigt vorher den Preis. /keepwarm hält den Cache warm.

Forked from obra/superpowers. Teaches Claude brainstorming, subagent driven development with built in code review, systematic debugging, and red/green TDD. Additionally, teaches Claude how to author and test new skills.

Read coding agents' session journals (omp, Claude Code, Codex): a session_read tool that reads, pages and searches a session by id and line, with asks shown in full, and the agent told its own session id

Live iOS Simulator and Android emulator screens in a pane, with tap, swipe and typing

Hand work to any agent CLI on your machine and see and control it from one pane.