sentry
1177Plugin Cursor
Bundles 8 skills · 661 tokens together
Sentry Plugin for Cursor to help with debugging including MCP and skill capabilities.
17,101 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Plugin Cursor
Bundles 8 skills · 661 tokens together
Sentry Plugin for Cursor to help with debugging including MCP and skill capabilities.
Skill Claude CodeCodex
Find code by the words it uses with the semantic-code MCP server's searchcode, and know when Grep or Read serves better. Use when you look for behaviour, a concept or a definition in a project's Python, Rust or Markdown files.
danielrosehill/Claude-KDE-Plasma-Plugin
Skill Claude CodeCodex
Use when the user wants to develop, scaffold, debug, package, or install a KDE Plasma 6 plasmoid (desktop or panel widget). Triggers on phrases like "build a plasmoid", "KDE widget", "Plasma 6 applet", "kpackagetool6", "QML plasmoid", "PlasmoidItem". Plasma 6 / Qt 6 only — does not cover the legacy Plasma 5 stack.
Skill Claude CodeCodex
Stability engineering rules for the Telegram Self Bot. Use when investigating freezes, stuck asyncio operations, AI/Save stability, watchdogs, task cancellation, diagnostics, or runtime recovery.
Baughn/machine-config-template
Command Claude Code
Run these commands, one at a time.
MCP server Claude CodeCodexCursor +2
Secure MCP runtime server for scanning and autofixing code issues. Remote server at mcp.qualityclouds.com.
codegraph-ai/codegraph-rules-for-agents
Cursor rule Cursor
Code intelligence via local code graph. Always try codegraph tools before grep for structural questions (callers, impact, deps, search).
MCP server Claude CodeCodexCursor +2
MCP server "pygdbmi-mcp-server" as configured in cnitlrt/pygdbmi-mcp-server. Runs locally from the pygdbmi-mcp-server Python package.
MCP server Claude CodeCodexCursor +2
Tool that create a graph of code to show dependencies between code entities (methods, classes and etc). Runs locally from the codegraph Python package.
aabhisrv/Spiderbrain.ai-Coremind
MCP server Claude CodeCodexCursor +2
Deterministic context layer for your codebase: change impact, blast radius, answers with receipts. Runs locally from the spiderbrain npm package. Needs 3 environment variables to run.
MCP server Claude CodeCodexCursor +2
The graph your agent actually follows — induce a behavioral spec from agent traces, then check, diff, and gate against it. Runs locally from the tracegraph npm package.
Plugin Claude Code
Bundles 3 skills, 1 hook, 1 MCP server · 183 tokens together
When a coding agent gets sick, let it ask CyberHuaTuo, fix the error, and keep the cure through MCP tools and agent skills.
Nishant-Chaudhary5338/mcp-toolkit
MCP server Claude CodeCodexCursor +2
Index any TypeScript/React repo (incl. monorepos) into a queryable code graph — npx CLI, HTTP/WS server, and MCP server. Reverse queries (who-renders/who-calls/find-references), blast-radius, cycles, dead-code orphans, symbol signatures, external (nodemo. Runs locally from the code-graph-indexer npm package.
Skill Claude CodeCodex
Set up and use Mushi Mushi, the bug mediator for AI-built apps: a user's bug report becomes a plain-English diagnosis and a paste-ready fix in Cursor or Claude Code over MCP. Use when installing the Mushi SDK, wiring the MCP server, managing Mushi keys, or asking how a Mushi feature works.
Skill Claude CodeCodex
Find the LLM call you didn't need — your GPT call is a regex. Static, zero-config linter that flags unnecessary GPT/Claude/AI API calls a regex, the stdlib, or a library already does (parsing dates, extracting emails/JSON, sorting, classifying with fixed labels). Runs locally, no model, no API key, nothing phones…
MCP server Claude CodeCodexCursor +2
Universal LSP MCP server. Runs locally from the @theupsider/lsp-mcp npm package.
Plugin Claude Code
Bundles 1 skill, 2 hooks, 1 MCP server · 148 tokens together
Skills that teach any agent to answer code questions structurally instead of reading whole files — symbol lookup, callers, imports and blast radius. Bundles the codeindex MCP server so install wires everything in one step.
MCP server Claude CodeCodexCursor +2
Search 25K+ verified engineering fixes by error or technology. For developers and AI agents. Runs locally from the fixgraph-mcp npm package.
Skill Claude Code
Orchestrate a full-project consistency audit using a parallel agent team. Spawns lane-specific auditors to cross-reference docs vs code vs tests vs infra, deduplicates findings, and writes a severity-scored audit report.
Skill Claude CodeCodex
Use this skill when the user asks to audit a codebase for LLM API calls (OpenAI, Anthropic — Python and TS/JS SDKs plus equivalent raw HTTP) and decide which calls can be replaced with deterministic logic. Activates on phrases like 'audit LLM usage', 'bust LLM calls', 'bust the LLM here', 'llm-bust this', 'do I…
Skill Claude CodeCodex
Expert skill for writing, debugging, and optimizing MQL5 code for MetaTrader 5 — Expert Advisors (EAs), custom indicators, scripts, services, libraries, and GUI panels. Use this skill whenever the user mentions MQL5, MQL, MetaTrader 5, MT5, MetaEditor, .mq5/.mqh/.ex5 files, Expert Advisor, EA, trading robot, custom…
Plugin Claude Code
Bundles 1 skill · 107 tokens together
Codebase intelligence for coding agents: fast multi-keyword scan, tree-sitter AST probing, context squeezing, and precise patch tools via MCP.
Skill Claude CodeCodex
Reviews and improves Debug.Log usage in Unity C# projects following structured logging principles: context tags, severity contracts, boundary-based placement, and criticality tiers. Detects common antipatterns (naked Debug.Log, logging in Update, stringly-typed errors), adds missing logs at system/state/error/external…
Plugin Claude Code
Bundles 1 skill · 115 tokens together
Check whether a repository agrees with itself, for Claude Code and Codex, then work through the findings one at a time. An exact layer finds broken links, dangling heading anchors, orphaned files, duplicate content, translations that have fallen behind and drift between docs and code, with no model, no network and no…
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: