Build, profile, debug, and refine iOS apps with SwiftUI and Xcode workflows — App Intents, Simulator debugging, performance profiling, memory leak detection, and on-device AI with Apple Intelligence, Foundation Models, and Core AI.
Live in-browser feedback loop for local web pages: serve a page with a comment widget injected, then turn the comments you leave into fix-it tickets Claude Code applies and verifies in place.
Repository debt elimination — heavyweight multi-agent workflows that cross-examine findings into consensus, then apply only the highest-ROI fixes: code, docs.
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search.
Deterministic code-graph MCP server: structural navigation, semantic find, impact analysis, and architecture decision records for the current repo. Zero infrastructure — the graph lives in .reposkein/ and the indexer binary is fetched on first run.
Token-efficient game-engine & build log analysis for Claude Code (CLI-first). Parses, deduplicates, and classifies huge Unreal/Unity/Godot/MSVC-UBT-MSBuild logs — search by severity/category, roll up by callsite, diff runs, locate file:line, and extract decisive scalar fields. No IDE required.
A comprehensive linter for Claude Code projects. Validates CLAUDE.md files, skills, settings, hooks, MCP servers, plugins, and more. Requires: npm install --save-dev claude-code-lint.
Debug Java programs interactively from the command line via the jdbg CLI: launch a program or attach to a running JVM (JDWP), set breakpoints, step through code, and inspect variables, expressions, threads, and exceptions. Stateful background sessions with structured (text/JSON) output. Cross-platform, native on…
11 1mo agoA
tokens not measured
originalApache-2.0
An MCP server specialized for VRChat avatar and world projects: it parses the asset YAML directly — including UdonSharp's split program/behaviour structure — to detect and repair broken references, prefab Variant override drift, and null wiring across prefabs, scenes, and materials. Built for AI agents, every fix runs.
Auto-runs a critical session post-mortem when Claude Code stops. Ships the analyze-session command, session-analyzer agent, and a Stop hook that triggers the review in-session (no external API calls). Requires Node.js 20 or newer on PATH.
Autonomous improvement engine for Claude Code. Runs an unbounded modify-verify-keep/discard loop against any mechanical metric. 9 subcommands: plan, debug, fix, security, ship, scenario, predict, and learn.
11 4mo agoA
tokens not measured
copy · 86%Apache-2.0
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: