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.
djscheuf/agentic-dev-ecosystem-template
Skill Claude Code needs its repo
Complete E2E test debugging workflow (composite orchestrator). Starts by reviewing the provided test failure evidence, then forms hypotheses, applies fixes, and verifies results for a presumed E2E playwright test suite.
elastic/semantic-code-search-mcp-server
MCP server Claude CodeCodexCursor +2 ✓ vendor
MCP server "semantic-code-search-mcp-server" as configured in elastic/semantic-code-search-mcp-server. Runs locally from the semantic-code-search-mcp-server npm package.
Skill Claude Code
Turn the recurring watch stuck-task pile into (1) a diagnosis of why each class is stuck, (2) the existing stuck rows actually cleared now, and (3) systemic prevention so it does not recur. Snapshots watch/incomplete/queue, buckets stuck tasks by failure class, dedups against already-tracked system work, unsticks each…
NUSGreyhats/ctf-agent-workstation
Skill Claude CodeCodex
Use when a single file falls into one of three trip-up cases the model reliably gets wrong without a recipe: (1) Corrupted-header repair where magic bytes / IHDR / SOI / EOI / CRC / central-directory fields have been clobbered and need precise byte-level reconstruction (PNG height-restore, JPEG marker repair, ZIP EOCD…
Skill Claude CodeCodex
Diagnose and fix tinycode environment issues — Ollama install, model health, tool-call capability, directories, agents, skills, connectivity, and container health.
lhx66/RTL-Auto-sim-verify-skills
Skill Codex
Use when verifying or debugging Verilog/SystemVerilog RTL with ModelSim, generating self-checking testbenches, running simulations, mining logs, or iterating fixes from vlog/vsim errors and [TBERROR] logs.
Plugin Claude Code
Bundles 1 skill, 1 agent, 4 hooks · 60 tokens together
Auto-runs a critical session post-mortem when Claude Code stops. Ships the analyze-session command, session-analyzer agent, and a Stop hook that triggers the review in-session (no external API calls). Requires Node.js 20 or newer on PATH.
Skill Claude CodeCodex
Use when Claude Code, Codex, or another terminal coding agent needs to control an MCU debug probe or inspect a live ARM Cortex-M target over SWD or JTAG, especially for board bring-up, flashing firmware, resetting the chip, halting or resuming execution, reading core registers, or dumping RAM and peripheral memory…
MCP server Claude CodeCodexCursor +2
Vibe reversing with IDA Pro. Runs locally from the ida-pro-mcp Python package.
Plugin Claude Code
Bundles 6 skills, 6 commands, 1 MCP server · 591 tokens together
Architectural telemetry for AI coding agents. Phase-scoped skills + slash commands over the raysense MCP server: scan + baseline at session start, blast-radius before edits, regression diff after, on-demand architecture audits, time-window drift detection.
Skill Claude CodeCodex
SLA path failure workflow — read slapaths.json, traceroute-first localization, ECMP handling, protocol triage.
fengyunzaidushi/claude-code-subagents
Command Claude Code
A debugging command that investigates a specified software problem and attempts to fix it. It uses root-cause analysis, tests possible explanations, and verifies the result.
Skill Claude CodeCodex
Checks AGENTS.md and SKILL.md files against the actual codebase for drift. Surfaces references to packages, directories, commands, or patterns that no longer match reality.
kaizen-yutani/playwright-autopilot
Plugin Claude Code
Bundles 3 skills, 4 agents, 1 MCP server · 107 tokens together
Playwright E2E test debugging and interactive browser exploration. Runs tests with action capture (DOM snapshots, network, console, screenshots), diagnoses failures, and provides browser tools for navigating, clicking, and inspecting pages through ARIA snapshots.
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 167 tokens together
Debug Java programs interactively from the command line via the jdbg CLI: launch a program or attach to a running JVM (JDWP), set breakpoints, step through code, and inspect variables, expressions, threads, and exceptions. Stateful background sessions with structured (text/JSON) output. Cross-platform, native on…
Plugin Claude Code
Bundles 15 skills · 2,364 tokens together
lifedever's curated Claude Code skills — macOS dev utilities, debug workflows, icon generation, diagramming, localization, and system diagnostics.
Skill Claude Code
Audit every agnostic-ai target against its vendor's current docs and report evidence-backed drift. Use for the recurring "are our adapters still true?" check, or when one tool ships a new surface.
Plugin Claude Code
Bundles 26 skills, 3 commands, 1 agent, 2 hooks · 948 tokens together
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques.
Skill Claude CodeCodex
A cause-and-effect analysis method from modern TRIZ, a problem-solving approach. It repeatedly asks why to trace a visible problem back through the events and conditions that caused it.
Skill Claude CodeCodex
Verifies that a feature is wired through all four layers (schema, API route, runtime, UI) before it may be called complete. Use when adding or auditing any feature — mirrors the connectivity-map method that caught the v1.21 autonomy gap.
Pengxiang-zhao/Shortcut-Anything
Skill Claude CodeCodex
Decompile Android APK/XAPK and extract deeplinks, shortcuts, share APIs with ADB validation. Use this skill whenever the user mentions: analyzing an APK, extracting deeplinks or deep links, decompiling Android apps, finding app shortcuts, reverse engineering APK/XAPK, smali analysis, ADB validation of URIs, batch…
Plugin Claude Code
Bundles 6 skills · 736 tokens together
An MCP server specialized for VRChat avatar and world projects: it parses the asset YAML directly — including UdonSharp's split program/behaviour structure — to detect and repair broken references, prefab Variant override drift, and null wiring across prefabs, scenes, and materials. Built for AI agents, every fix runs.
Skill Claude CodeCodex
Hunt for bugs in distributed consensus protocol implementations using a 2-agent strategy+testgen pipeline. Use when targeting consensus protocols (Raft, PBFT, HotStuff, Tendermint, etc.) for automated vulnerability discovery.
Skill Claude CodeCodex
Use when receiving UAT feedback, bug reports, user testing results, stakeholder feedback, QA findings, or any batch of issues to investigate. Investigates each item BEFORE creating issues, classifies by type and priority, creates well-formed GitHub issues with proper project board integration.
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: