20,069 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 2 skills, 1 command, 2 agents, 1 MCP server · 487 tokens together
Local-first LLM branching, debugging & context offloading. Treat AI context windows like a Git repo — capture, branch, regression-test LLM calls as a DAG, and archive context as encrypted, restorable capsules. Teaches Claude when and how to drive ForkMind.
Skill Claude CodeCodex
Skill "docs" from SpecLeft/specleft, covering specleft cli reference, setup, workflow, quick checks and safety.
MCP server Claude CodeCodexCursor +2
MCP server for link checking using linkinator. Runs locally from the linkinator-mcp npm package.
Skill Claude CodeCodex
Set up and use Mushi Mushi, the bug mediator for AI-built apps: a user's bug report becomes a plain-English diagnosis and a paste-ready fix in Cursor or Claude Code over MCP. Use when installing the Mushi SDK, wiring the MCP server, managing Mushi keys, or asking how a Mushi feature works.
MCP server Claude CodeCodexCursor +2
MCP server for Allure TestOps — projects, launches, test cases, test results, defect categories. Runs locally from the allure-testops-mcp Python package. Needs 3 environment variables to run.
Skill Claude Code
Given a benchmark repository URL (agentic envs like arc-agi, memory/eval benchmarks like longmemeval, QA/code/tool-use benchmarks, etc.), orchestrate the creation of a full Claude Code plugin that benchmarks the current harness setup against it. Wraps the babysitter:babysit skill with the benchmark-plugin-creator…
Skill Claude CodeCodex
Operate only in authorized scope: bug bounty targets explicitly in scope, owned systems, defensive reviews, or labs. Decline or pause on requests involving unauthorized access, stealth, persistence, service disruption, credential abuse, real data theft, or abuse of third-party systems.
Skill Codex
Proves that agent work is actually done: each claim becomes a ledger row with a gate that was executed, captured raw evidence, and a status a builder is not allowed to write for itself. Use when a technical result must be auditable later — shipping or migrating something users depend on, a change whose failure is…
Skill Claude CodeCodex
TDD-first spec management for AI coding workflows. Use this skill when the user explicitly mentions specs, forging, or structured planning: says "forge", "forge a spec", "write a spec for X", "create a spec", "plan X as a spec", "resume", "what was I working on", "spec list/status/pause/switch/activate", "implement…
Skill Claude Code
How to run and drive this app to verify UI/server changes at runtime.
Plugin Claude Code
Bundles 47 skills, 1 hook · 1,212 tokens together
Cross-platform engineering skills across the software lifecycle, with auditable documents, task-sized workflows and self-contained Codex installation.
Plugin Claude Code
Bundles 1 skill · 221 tokens together
Right-sized code, verified before it ships. Risk-tiered engineering judgment for AI coding agents: convention detection, blast-radius tiers, mandatory verification, and a scannable logbook for deliberate shortcuts.
u9401066/template-is-all-you-need
Skill Claude Code
A test-suite generation workflow for software projects. It includes static checks, unit tests, integration tests, end-to-end tests, coverage reports, type checking, linting, security scanning, and dead-code detection.
Skill Claude Code
Test an Android app on a real phone or an emulator using adb. Use when the user wants to install an APK they just compiled, walk through the app's screens, check the on-screen text, reproduce a bug, capture screenshots, read crash logs, or set up an Android testing environment from scratch. Covers both a physical…
endorphin-ai/claude-code-teams
Skill Claude Code
Go testing skill with table-driven tests, httptest, testify, and integration testing patterns. Use when writing or running Go backend tests.
JSchOBL/agentic-ai-learning-journey
Skill Claude Code
Run the pytest suite, report pass/fail counts and coverage, and identify untested code. Use when the user asks to run tests, check test coverage, or verify that changes didn't break anything.
Skill Claude CodeCodex
Use when completion depends on an end-to-end outcome across components, environments, or external systems.
Skill Claude CodeCodex
Testing strategies including unit tests, integration tests, E2E tests, mocking, coverage analysis, and TDD workflow. Trigger when users need help writing tests, choosing testing frameworks, implementing mocking strategies, or setting up test infrastructure.
giltotherescue/velocity-agent-skills
Skill Claude CodeCodex
Use when a branch, worktree, local app, or cloud-agent task needs a staged test environment without disturbing the main checkout, especially for browser-facing web app work. Helps agents choose and set up the right strategy for browser/app testing across JavaScript/TypeScript, Python, PHP, Docker Compose, local…
ironbee-ai/ironbee-devtools-skills
Skill Claude Code
CLI for driving an Android emulator (AVD) over adb. Use when the user needs to connect to an emulator (attach to a running one or boot/manage an AVD), tap/swipe/type on the UI, read the UI/accessibility tree, take screenshots or screen recordings, capture logcat, capture HTTP(S) requests in-process (Frida OkHttp hook…
redamancy231-create/claude-skills
Skill Claude Code
A test-first review process for new research ideas, trading strategies, paper topics, models, architectures, or data pipelines. TDD means defining tests or checks before building the idea.
bhaumikmaan/claude-code-master-skills
Skill Claude Code
Adversarial verification of code changes. Tries to break implementations rather than confirm they work. Produces structured PASS/FAIL/PARTIAL verdicts with evidence. Use when verifying code changes, after non-trivial implementations, before reporting task completion, or when asked to check if something works.
Plugin Claude Code
Bundles 3 skills · 288 tokens together
Universal E2E and manual acceptance testing for any repo: test-init generates project test plans (TESTSE2E.md, TESTSMANUAL.md), test-e2e executes them autonomously, test-manual conducts them with you at the controls. Every run writes a timestamped protocol file.
Plugin Claude Code
Bundles 2 skills, 1 agent, 1 hook · 395 tokens together
Verification gate for AI work — one run file, one independent validator, evidence-gated close. CLI-only transport via the anchored binary over Bash, no MCP. Slash commands: /a:run /a:setup.
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: