15,528 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 Claude Code
Bundles 38 skills · 1,427 tokens together
38 engineering discipline skills for Claude Code & OpenAI Codex — research, quality gates, testing patterns, deployment, learning, gap analysis, spec sync, and more. Extracted from real-world development.
Skill Claude Code
A specialist for diagnosing and fixing invalid OpenClaw configuration and container-startup problems.
Cursor rule Cursor
CodeGraph MCP usage guide — when to use which tool.
Skill Claude CodeCodex
Run a subagent-first structured improve-verify loop in OpenCode. Activate with /autoresearch or specialized modes like /autoresearch:plan, /autoresearch:debug, /autoresearch:fix, /autoresearch:learn, /autoresearch:predict, /autoresearch:scenario, /autoresearch:security, /autoresearch:ship. Supports recursive…
cacheforge-ai/cacheforge-skills
Skill Claude CodeCodex
Kubernetes Cluster Triage & Diagnostics — instant AI-powered incident triage via kubectl.
Cursor rule Cursor
Cursor rule "mcp-debugging" from giantswarm/mcp-prometheus, covering debugging mcp-prometheus via mcp-debug, core debugging tools, debugging workflow, 1. verify all services are running and 2. check mcp server registration.
MCP server Claude CodeCodexCursor +2
Debug probe Model Context Protocol server for AI agents and developer tooling. Runs locally from the dbgprobe-mcp-server Python package. Needs 9 environment variables to run.
Skill Claude CodeCodex
Diagnose and fix Single Step Instrumentation (SSI) issues on Kubernetes — SSI automatically instruments applications for APM without code changes. Only use if the agent and SSI are already configured but traces are missing or instrumentation is not working.
MCP server Claude CodeCodexCursor +2
Java profiling MCP via jcmd/jfr/jps. Diagnose performance, analyze threads, inspect JFR recordings. Runs locally from the javaperf npm package.
Skill Codex needs its repo
Audit and repair exported n8n workflow JSON with deterministic safety and outcome-contract checks. Use when reviewing AI-generated or customer-facing n8n workflows before deployment, investigating Vibeflow VF000-VF013 findings, adding kill switches or human handoffs, checking secrets, retries, webhook exposure, money…
Skill Claude Code
End-to-end incident investigation workflow that fetches logs and performs root cause analysis. Use when a user wants to investigate incidents, analyze job failures, fetch and analyze logs in one workflow, or debug infrastructure issues. Combines log-fetcher, root-cause-analysis and context-fetcher into a unified…
Skill Claude CodeCodex
Triage bugs reported in chat/issues, search for duplicates, file or update GitHub issues with full context, and push fix PRs.
Skill Claude CodeCodex
Structured workflow for profiling and optimizing Python code — CPU hotspots, memory usage, and benchmark-driven validation. Use this skill whenever the user asks to make Python code faster, reduce memory usage, profile performance, find bottlenecks, optimize hot paths, reduce allocations, or investigate why something…
Plugin Claude Code
Bundles 1 skill, 1 command, 8 agents · 494 tokens together
FinTech AI closed-loop debugging framework: threat-model → detect → reproduce (attack PoC) → fix → verify (invariants) → recycle, for financial correctness & security bugs.
Skill Claude CodeCodex
Diagnose and recover a live epistemic-graph engine (the AI-native database): engine down / socket refused, host-daemon crash-loop, circuit-breaker open, backend-type errors, zombie containers, duplicate Swarm tasks, slow first boot. Use when the KG is unreachable, ingestion stalls, go tools error, or a deploy left the…
fermonterom/claude-testing-kit
Command Claude Code
Escanea el proyecto, valida build, env vars, seguridad, tests, y da un score 0-100 con semaforo.
jacinthpaul/Claude-Certified-Architect
Skill Claude Code
Map an unfamiliar module's structure and dependencies, returning a summary.
MCP server Claude CodeCodexCursor +2
MCP server "rust-analyzer" as configured in coherentforge/CambiOS. Runs mcp_rust_analyzer with /Users/jasonricca/Library/CloudStorage/OneDrive-Personal/Synthesis/coding/Tooling/mcp-rust-analyzer/.venv/bin/python3. Needs 1 environment variable to run.
gylove1994/superpowers-deepseek-v4
Plugin Claude Code
Bundles 19 skills, 1 hook · 744 tokens together
Superpowers DeepSeek v4: composable agent skills for TDD, debugging, and collaboration. Independently maintained; not identical to obra/superpowers.
MCP server Claude CodeCodexCursor +2
Model Context Protocol SDK. Runs locally from the mcp Python package.
Plugin Claude Code
Bundles 1 skill · 72 tokens together
Static correctness linter and quality orchestrator for Claude Code plugins, skills, and hooks. Catches invalid hook schemas, bad frontmatter, YAML corruption, and token inefficiency. Delegates description quality to skill-creator.
Skill Claude CodeCodex
Detect silent agent failures and memory degradation. Use when asked for an agent health check, when agent behavior seems off or output quality drops, after long unattended runs, or as part of a scheduled maintenance pass.
diegomarino/awesomic-cursor-rules
Cursor rule Cursor
Creating and editing log messages.
aws-samples/sample-aws-devops-agent-claude-plugin
Plugin Claude Code ✓ vendor
Bundles 4 skills, 4 commands, 2 MCP servers · 397 tokens together
Investigate incidents, optimize costs, review architecture, and map topology with the AWS DevOps Agent — fully integrated into Claude Code via MCP, with skills that auto-route incidents to the right workflow.
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: