15,549 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.
BKF-Gitty/openclaw-update-runbook
Skill Claude CodeCodex
Use when updating OpenClaw or debugging an OpenClaw instance after an update. This skill acts as a structured update runbook with emphasis on gateway startup, service-manager state, plugin registry and install drift, bundled-vs-npm/clawhub plugin confusion, stale config carried across upgrades, channel health, task…
Skill Claude CodeCodex
Rebound recomposition budget monitor skill for Compose performance analysis. Guides budget class interpretation, violation diagnosis, skip rate analysis, stability optimization, CLI usage, and IDE plugin workflow. Use this skill whenever the user mentions recomposition, budget, violation, Rebound, skip rate, jank…
Skill Claude CodeCodex
Use when analyzing Android ANR or bugreport traces (anr, traces.txt, Waiting Channels, DALVIK THREADS, SIGQUIT stacks), especially when root-cause evidence and lock/Binder chain mapping are required for com.thunder. or other Android projects.
Cumulocity-IoT/cumulocity-skills
Skill Claude CodeCodex
Analyze Angular / Cumulocity Web SDK code for anti-patterns, bugs, and quality issues. Use when reviewing components, services, or modules for code quality, maintainability, performance, and correctness. Covers TypeScript best practices, Angular idioms, C8Y SDK usage patterns, and project-specific conventions.…
Skill Claude CodeCodex
Reverse engineering meta-cognitive activation engine. Manages attention allocation, noise suppression, task-mode routing, object typing, hypothesis branching, mental model switching, and analysis boundary judgment at a meta level. Use when performing reverse engineering, binary analysis, malware analysis, obfuscation…
HankLEE-1/security-skills-consolidated
Skill Claude CodeCodex
A guide to reverse engineering, the practice of examining software to understand how it works, using tools such as radare2.
Skill Claude CodeCodex
Use when Claude wants an adversarial review, design critique, plan critique, or second-opinion debugging from Codex AND wants to engage with the findings rather than receive a one-shot report. Sets up an Epic bead, asks Codex to file each finding as a child bead, then runs a back-and-forth where Claude responds to…
kings0527/web-reverse-engineering-skill
Skill Claude CodeCodex
A guide to analyzing how websites work in the browser, including their JavaScript, network requests, and anti-automation protections.
Skill Claude CodeCodex
Systematic approach for complex refactoring using dependency graphs, leaf-first execution, and revert-on-failure to keep the codebase always shippable.
Skill Codex
A diagnostic guide for why JavaScript packages from node_modules are placed in a uni-app mini-program's main bundle instead of a subpackage bundle. uni-app is a framework for building apps and mini-programs from one codebase.
ConnieHan2019/code-removal-skill
Plugin Claude Code
Bundles 1 skill · 119 tokens together
Remove dead code, deprecated handlers, unused modules and orphan symbols safely and completely. Enforces a 3-role workflow (supervisor / executor / blind-reviewer), manifest-based review gates, layered build validation, and hard acceptance criteria.
Plugin Claude Code
Bundles 1 skill · 0 tokens together
Registers lintropy lsp as a Language Server so Claude Code sees lintropy diagnostics live while editing.
Skill Claude CodeCodex
Diagnose codebase issues from any input — ticket, freeform, paste. Traces the codebase autonomously, confirms root cause with evidence, outputs diagnosis, then waits for user to confirm before fixing. NO fixes before root cause is confirmed.
Skill Claude CodeCodex
An authorised reverse-engineering workflow for examining local software samples and recovering how they work. Reverse engineering means studying compiled or packaged software, such as an APK, ELF, PE, or firmware image, to infer its logic.
Skill Claude CodeCodex
Reverse-engineer a website's internal APIs, encrypted endpoints, WebSocket streams, and obfuscated JavaScript. Activates when the target data isn't in the HTML, when the site uses encrypted CloudFront/CDN payloads, when real-time streaming data is needed, or when the scrape skill's Phase 0-1 finds API calls that are…
Skill Claude CodeCodex
You are a CI triage agent. A CI job has failed. Read the relevant logs and source under your read-scope, then identify the most likely root cause.
Plugin Claude Code
Bundles 1 skill, 1 command · 106 tokens together
Deterministic 0-100 health score and agent fix-loop for Android Jetpack Compose, wrapping detekt + compose-rules. Bundles the compose-doctor skill and the /compose-doctor command.
Skill Claude CodeCodex
A troubleshooting guide for Kubernetes access permissions and resource limits. Kubernetes is software for running and managing containers, while RBAC controls who can do what and ResourceQuota limits resource usage.
Baughn/machine-config-template
Command Claude Code
Run these commands, one at a time.
Command Claude Code
Health-check the wiki install chain (paths, hooks, wiring, git).
Skill Claude CodeCodex
Meta-skill that coaches the AI + user pair through any operational task (deploy, pipeline, provision, migrate, rollback, diagnose, debug-wiring) in any stack, then crystallizes the successful workflow into a project-local reusable skill. Asks WHAT the user wants to achieve, proposes an access menu (CLI > API > Web)…
Skill Claude CodeCodex
Production-hardened practices for building, debugging, and optimizing LLM agents with tools, streaming UI, and multi-turn sessions. Covers dual-store transcripts, artifact ownership, phase gating, orchestration tiers, failure classification, and root-cause fixes over patches. Use when designing agent loops, fixing…
Skill Claude Code
Validates all Mermaid diagram blocks in a markdown file using the Mermaid Chart MCP tool and fixes broken diagrams in place.
MCP server Claude CodeCodexCursor +2
MCP server for network diagnostics and service health checks — 235 tools spanning ping/DNS/port/traceroute/TLS plus reachability probes for 180 self-hosted services (databases, queues, observability, arr stack, and more). Runs locally from the mcp-nettools 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: