18,394 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.
mashhoorahdal/shipd-olympus-skill
Skill Claude CodeCodex
Use when creating or reviewing a shipd.ai Olympus quest submission — picking a candidate GitHub repo, designing a challenge task hard enough for the ≤50% pass-rate bar, writing the test patch, solution patch, test.sh, or Dockerfile, or when a platform check fails (naming collisions, Dockerfile warnings, description…
Plugin Claude Code
Bundles 12 skills · 992 tokens together
Specification-Driven Development — a structured workflow for Claude Code that enforces specify → clarify → plan → tasks → implement → validate before writing code.
Plugin Claude Code
Bundles 1 skill · 47 tokens together
Adds a solid-RED opsx:tdd gate to OpenSpec (between opsx:propose and opsx:apply). Converts a change's tests.md into REAL failing tests (real render, real data-testids, real assertions) that fail only because the implementation is missing. No expect.fail placeholders.
Plugin Claude Code
Bundles 6 skills, 3 agents, 1 hook · 379 tokens together
sonmat — External verification system. Six verification axes (guard/inspect/witness/punch/devil/scribe) + autoloop orchestration. Discovery-led depth, protocol-isolated intent-artifact comparator (witness), post-work persistence layer (scribe).
Plugin Claude Code
Bundles 1 skill · 73 tokens together
Visual comparison, accessibility audit, layout regression, and device interaction for React Native and Android apps.
Skill Claude CodeCodex ✓ vendor
Run vLLM Buildkite CI-equivalent tests locally on NVIDIA GPUs using the current shell environment. Use when the user asks to run CI tests locally, reproduce CI failures, run a specific test file or test area, or match Buildkite test behavior.
vlad-ryzhkov/ai-context-engineering-for-qa
Agent Claude Code
Code generator that converts test plans into compilable automated tests in Kotlin or Java.
Skill Claude CodeCodex
Use this skill to aggregate and visualize test RESULTS into dashboards/reports — a self-contained HTML dashboard from JUnit XML (embedded zero-dep Python generator), Allure (rich reports with history/trends), k6 → Grafana for performance, and CI-native summaries (GitHub Actions job summary, test-reporter actions…
Skill Claude CodeCodex
A skill for creating test cases for cloud-product features and interfaces. It can cover normal and error situations, with optional interface-level cases and automation code.
Cursor rule Cursor needs its repo
Comprehensive Effect-TS service architecture patterns covering stores, usecases, handlers, and testing for building scalable applications.
python-developer-tooling-handbook/claude-plugins
Plugin Claude Code
Bundles 1 skill · 26 tokens together
Set up Python projects with modern tooling (uv, pytest, ruff, pre-commit).
nathanvale/side-quest-marketplace-old
Agent Claude Code
Review test code for resource cleanup, mock hygiene, and best practices in Bun/Node.js projects. Use after writing tests or when debugging flaky tests.
Plugin Claude Code
Bundles 2 skills, 4 agents · 594 tokens together
Loop Engineering portable: bucle autónomo que revisa un proyecto por flujos de ejecución (GitNexus), escribe tests (test-first), arregla lo seguro en worktrees aislados, lo verifica con un evaluador adversarial independiente y abre PRs — nunca auto-mergea. Incluye la skill /forja y 4 subagentes…
RahSwe/claude-code-full-dev-workflow
Plugin Claude Code
Bundles 3 commands, 8 agents, 3 hooks · 234 tokens together
Complete feature development workflow with code mapping, TDD, task-based implementation, multi-agent review, UI verification, PR management, and state persistence.
Agent Claude Code
A coding role that turns detailed plans into code, tests the result, and fixes problems found during review.
Plugin Claude Code
Bundles 20 skills, 2 agents, 3 hooks, 1 MCP server · 2,022 tokens together
Sumo QA — a senior-QA-shaped MCP server for pre-coding QA planning, TDD scaffolding, mutation-testing follow-up, code review, and test-data discovery.
Anselmoo/mcp-ai-agent-guidelines
Skill Claude Code
Fix Codecov patch coverage gaps reported on a pull request. Use when Codecov bot flags missing or partial lines in a PR comment, when patch coverage is below the project threshold (≥87.55%), or when coverage regresses after new code is merged. Covers reading the Codecov report, identifying uncovered lines per file…
MCP server Claude CodeCodexCursor +2
Multi-language MCP server for API testing with TypeScript/Playwright, JavaScript/Jest, Python/pytest support. Runs locally from the @kirti676/api-tester-mcp npm package.
MCP server Claude CodeCodexCursor +2
Gremlin MCP Server. Runs locally from the @gremlin/mcp-server npm package.
MCP server Claude CodeCodexCursor +2
Claude-compatible MCP server for Appium (Android + iOS). Runs locally from the appium-mcp-server npm package.
MCP server Claude CodeCodexCursor +2
Model Context Protocol server for MagicPod integration. Runs locally from the magicpod-mcp-server npm package.
electron-stagewright/electron-stagewright
MCP server Claude CodeCodexCursor +2
Agent-native MCP server for driving, inspecting, and asserting on real Electron desktop apps. Runs locally from the @electron-stagewright/core npm package.
Plugin Claude Code
Bundles 5 skills · 324 tokens together
AI-assisted pipeline that turns product specs into human-reviewed test plans and executable Playwright automation.
Plugin Claude Code
Bundles 1 skill · 72 tokens together
Mine for hidden bugs that pattern-based auditors miss — logic errors, broken assumptions, state machine gaps, and semantic fragility.
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: