15,663 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.
6maple/mcp-for-chatgpt-web-tunnel
MCP server Claude CodeCodexCursor +2
MCP server "codegraph" as configured in 6maple/mcp-for-chatgpt-web-tunnel. Launched with codegraph serve --mcp.
Agent Claude CodeCursor
Decky debugger for Steam UI and plugin runtime issues. Use when D-pad/controller focus is wrong, modals behave oddly, layout clips/drifts, durable styles regress, or logs must prove root cause before fixes. Enforces focus-graph-first triage, evidence-backed geometry fixes, and a self-contained log-capture runbook so…
Plugin Claude Code
Bundles 4 skills, 2 agents · 166 tokens together
Control Zen for browsing, web testing, and debugging. Fill forms, capture network and console activity, take screenshots, and inspect console and network activity.
Skill Claude CodeCodex
Use when stuck on a long, cryptic, or environment-sensitive error (build failures, CUDA/toolchain mismatches, distributed-training crashes) that you cannot solve from memory. Searches the Hindsight commons for a known fix and reports whether it worked.
MCP server Claude CodeCodexCursor +2
TypeScript MCP server for Frida 17 dynamic instrumentation. Runs locally from the frida-mcp npm package.
InitialXW/devops-agent-networking
Skill Claude CodeCodex
Methodology for investigating network CONNECTIVITY / reachability problems.
MCP server Claude CodeCodexCursor +2
Progressive CLI and optional MCP code intelligence powered by CodeGraph. Runs locally from the @team-harness/code-deep npm package.
MCP server Claude CodeCodexCursor +2
MCP server "hardware-logging" as configured in gurul/hardware-logging. Runs locally from the hardware-logging Python package.
Plugin Claude Code
Bundles 1 skill · 102 tokens together
DevTools for any WebView — no remote-debugging port required. Works in Safari/iOS WebView/Lark Web App and more.
MCP server Claude CodeCodexCursor +2
The static analyzer your AI agent reads — fix-ready, machine-readable scan reports over MCP. Runs locally from the codemore npm package.
Plugin Claude Code
Bundles 8 skills, 2 MCP servers · 428 tokens together
MCP server for automating and debugging Excel add-ins running in WebView2 via the Chrome DevTools Protocol.
MCP server Claude CodeCodexCursor +2
AI code impact analysis — dependency graphs, cascade detection, and build gates for AI agents. Runs locally from the @syke1/mcp-server npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "mcp-pyrefly" as configured in kimasplund/mcp-pyrefly. Runs locally from the mcp-pyrefly Python package.
Plugin Claude Code
Bundles 3 commands, 1 agent, 1 MCP server · 206 tokens together
Multi-language debugging plugin for Claude Code using Debug Adapter Protocol. Debug JavaScript/TypeScript, Python, Go, and Rust with real breakpoints, stepping, and variable inspection.
MCP server Claude CodeCodexCursor +2
The XBSL (1C:Element) toolkit: a linter with autofixes, LSP, MCP server, documentation search, project index, metadata scaffolding, translation into English spellings, and a VS Code extension. Runs locally from the xbsl Python package.
MCP server Claude CodeCodexCursor +2
MCP server "dotnet-debugger-mcp" as configured in nevse/dotnet-debugger-mcp. Launched with DotnetDebugger.Mcp.
Plugin Claude Code
Bundles 2 skills · 246 tokens together
Defense against LLM Rust failure modes: 59 categories of bugs that survive rustc, clippy, and cargo test — async cancellation, unsafe/FFI, concurrency, crypto, supply-chain, tests-that-pass-by-luck, semantic conformance, and systemic performance cost. Ships the rust-intel skill plus /rust-intel:audit, /rust-intel:fix.
Skill Claude Code
Read-only environment diagnostic for a solo-lane repo: whether the tools the hooks and skills assume are installed, and whether the guardrails and the pre-commit really fire here or are silently skipping, each gap reported with a copy-paste fix.
Skill Claude CodeCodex
Audit CLAUDE.md against .claude/settings.json. Reports which rules are enforced by hooks/permissions and which are prose, plus context cost, import resolution, contradictions, and structure. Use when the user asks to audit, check, lint, or grade their CLAUDE.md, or asks whether their Claude Code rules are enforced.
Skill Claude CodeCodex
Activates a structured, hypothesis-driven debugging loop. Use this skill whenever the user reports a bug, unexpected behavior, or runtime error and wants help diagnosing the root cause - especially for bugs that are hard to reproduce or where the fix isn't obvious. Trigger on phrases like: "debug this", "figure out…
Skill Claude CodeCodex
Use when working with Windows (cmd/PowerShell console, MINGW64, script installation): stdout encoding (cp1251 vs UTF-8, UnicodeEncodeError on ✓/Cyrillic), CRLF/LF when writing files (md5 checks of mirrors), UTF-8 BOM for PowerShell 5.1, npm.cmd instead of npm, venv Scripts vs bin, PYTHONIOENCODING/PYTHONUTF8. Verified…
yuezhongtao/linux-profiler-tool
MCP server Claude CodeCodexCursor +2
Linux Performance Profiler with MCP Protocol Support and Process Profiling. Runs locally from the linux-profiler-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server for CUCM operational debugging: DIME logs, AXL config, RIS device status, PerfMon counters, service health, packet capture, and pcap analysis. Runs locally from the @calltelemetry/cisco-cucm-mcp npm package.
thomasproject-stack/signal-prospector
MCP server Claude CodeCodexCursor +2
Prospector is a tool to analyse Python code by aggregating the result of other tools. Runs locally from the prospector Python package.
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: