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.
Skill Codex
A read-only investigation mode for finding root causes, semantic drift, or incomplete capabilities before making changes. It prevents project files from being edited during diagnosis.
Skill Claude CodeCodex
Use when agent skill entrypoints for Codex and Claude Code may be broken, duplicated, unmanaged, or drifting away from /.skm, and you want a structured diagnosis before fixing anything.
soderlind/wordpress-agent-plugin
Skill Claude CodeCodex
Run mutation testing on WordPress plugins and themes to find weak tests — Pest --mutate or Infection for PHP, StrykerJS for JavaScript — then triage surviving mutants into concrete test improvements.
Skill Claude CodeCodex
When a class of bug keeps slipping through tests, run a coverage-matrix audit first, then fan out fix agents per gap — don't whack-a-mole individual failures.
Skill Claude CodeCodex
Diagnose live Kubernetes failures (CrashLoopBackOff, OOMKilled, NodeNotReady, ImagePullBackOff, Network/CNI failures, HPA starvation, DNS failures, pending pods) with an evidence-first procedure: capture context, collect signals (events/status/logs), rank falsifiable hypotheses, verify one variable at a time, fix with…
billylui/wordpress-performance-skills
Plugin Claude Code
Bundles 2 skills · 287 tokens together
Audit and fix performance on live WordPress sites across whatever stack they actually run — page builders, caching layers, CDNs and managed hosts. Fingerprints the stack, separates origin from edge TTFB, and applies fixes only under a guarded write loop with a rollback for every change.
Skill Claude CodeCodex
A systematic engineering methodology for coding agents. Teaches where to look when researching a codebase, how to plan before coding, how to verify work instead of assuming it is done, how to debug from evidence, and how to sustain long autonomous tasks across sessions without losing state. Use when writing or…
Plugin Claude Code
Bundles 2 skills · 159 tokens together
Audit agent skills for CLI drift — finds skills that call external tools with flags or subcommands the installed version no longer accepts.
torrresagus/cloudwatch-debugger-skill
Skill Claude Code
Debug production issues and monitor AWS infrastructure via CloudWatch. Use when the user reports errors, wants to investigate production behavior, check logs, debug OAuth, API errors, ECS tasks, database issues, WAF blocks, or any production incident. Also use when the user says "check logs", "what's failing", "why is…
Skill Claude CodeCodex
GitHub development workflow for planning, implementing, validating, and reviewing code changes. Plans a feature or bug as a GitHub issue, implements an issue and opens a pull request, runs a repository's validation checks before a PR, reviews a pull request, plans an epic as phased issues, researches a technical…
Command Claude Code
Postmortem analysis of cluster failures → OPTIMIZE PROMPTS to work for EVERY use case.
Skill Claude CodeCodex
Agentic LLDB fuzzer and crash-triage toolkit for Apple Mach-O on arm64(e). Use this skill whenever a user mentions alf, wants an AI agent to drive LLDB over MCP, asks about triaging a crash on macOS, wants to fuzz a Mach-O target with LLM guidance, is debugging a macOS kernel via Virtualization.framework / KDP /…
Plugin Claude Code
Bundles 14 skills, 2 agents, 1 hook, 1 MCP server · 1,346 tokens together
Skills, agents, and commands for deploying, operating, and troubleshooting Ceph storage clusters — cluster setup, OSD/MON/MGR management, pool and CRUSH map configuration, health diagnostics, and day-2 operations.
Skill Claude CodeCodex
Systematically diagnose a failing test instead of guessing at fixes.
Skill Claude Code
Debug a live Node.js process via CDP — connect to --inspect, set TypeScript breakpoints, step through code, and inspect variables at runtime. Use when the user mentions debugging, --inspect port, breakpoints, wants to trace a bug, inspect what a variable holds, or understand why code behaves unexpectedly at runtime.
Skill Claude CodeCodex
Capture a failed or blocked task before it disappears. Categorizes the failure mode, extracts what was learned, and generates either a retry packet with the root cause fixed or an escalation message with specific decision points. Use whenever an agent returns a blocker, error, or partial result.
Skill Claude CodeCodex
Check whether a project's documentation still matches its code, and report stale or wrong claims with suggested fixes. Use this after editing, renaming, moving, or deleting source files, CLI flags, environment variables, or functions, to catch docs you may have just made inaccurate; when the user asks whether the…
Skill Claude CodeCodex
Navigate a codebase through a local tree-sitter knowledge graph instead of grepping blindly. Use when asked how a medium-or-large codebase works, where a symbol is defined, what calls what, how two modules connect, or when planning a refactor that spans files. Requires the external graphify Python CLI; degrades to…
Skill Codex
Delegate independent, bounded work to specialized reader and writer subagents with explicit ownership and parent verification. Use when parallel work can be scoped and verified independently.
Plugin Claude Code
Bundles 2 skills, 2 hooks · 23 tokens together
Catches false claims from AI coding agents. Verifies that actions were actually performed.
Command Claude Code
Analyze details about a Component Readiness regression and suggest next steps.
MCP server Claude CodeCodexCursor +2
Sentry's hosted MCP server: lets the agent search and read issues, errors and traces. Remote server at mcp.sentry.dev.
Plugin Claude Code
Bundles 6 skills, 1 hook · 290 tokens together
Orchestrator skills, agent prompts, and state management for the Jira autofix pipeline.
Skill Claude CodeCodex
This skill should be used when the user asks to 'debug this failure', 'find root cause', 'compare passed vs failed', 'trace X values', 'analyze fmod vs vmod mismatch', or needs hardware simulation Root Cause Analysis methodology.
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: