Testing

27,851 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.

commit-helper

169

agentforce314/clawcodex

Skill Claude CodeCodex

Generate a conventional-commit message from staged changes.

not rated 892 +6 2d ago A 10 tokens original MIT

react-svg AGENTS.md

170

tanem/react-svg

Instructions file CodexOpenCode

AGENTS.md instructions for tanem/react-svg, covering agents.md, writing, architecture, build & test and releases.

not rated 883 5d ago A 1,330 tokens original MIT

SoftInstigate/restheart

Instructions file GitHub Copilot

Copilot instructions for SoftInstigate/restheart, covering restheart ai coding agent instructions, project overview, architecture & module structure, plugin architecture (critical) and build & test workflows.

not rated 883 yesterday A 2,124 tokens AGPL-3.0

tophant-ai/aibeat

Skill Claude CodeCodex

Use when a user needs help choosing Promptbeat attack goals, risk types, scenarios, seed files, dataset subscriptions, compliance profiles, or a small smoke-test scope.

not rated 877 +1 11d ago A 39 tokens

marmite-development

173

rochacbruno/marmite

Skill Claude CodeCodex

Guidelines and workflows for contributing to the marmite codebase - covers code quality, testing, architecture patterns, and contribution checklists.

not rated 872 7d ago A 31 tokens AGPL-3.0

proofshot CLAUDE.md

174

AmElmo/proofshot

Instructions file

Instructions for AmElmo/proofshot, covering proofshot cli, quick reference, architecture, key conventions and command lifecycle.

not rated 857 +2 4mo ago A 1,221 tokens original MIT

pipelock AGENTS.md

175

luckyPipewrench/pipelock

Instructions file CodexOpenCode

AGENTS.md instructions for luckyPipewrench/pipelock, covering agents.md - pipelock contributor guide, quick reference, capability surface, build, test, lint and architecture.

not rated 834 +11 changed yesterday A 2,745 tokens original Apache-2.0

test-tools

176

utensils/mcp-nixos

Command Claude Code

Test MCP NixOS Tools (project).

not rated 823 +11 changed today A 9 tokens original MIT

imgui-java AGENTS.md

177

SpaiR/imgui-java

Instructions file CodexOpenCode

AGENTS.md instructions for SpaiR/imgui-java, covering agents.md, what this repo is, project layout, build & test and upgrading dear imgui or an extension.

not rated 820 5d ago A 3,576 tokens original MIT

lighteval-porter

178

groq/openbench

Agent Claude Code

Use this agent when you need to port an evaluation benchmark from the LightEval framework to openbench. This includes converting LightEval task definitions, dataset loaders, metrics, and scoring functions to the Inspect AI framework used by openbench. The agent should be invoked when the user mentions porting…

not rated 813 10d ago A 305 tokens original MIT

rust-skills

179

sockudo/sockudo

Skill Claude CodeCodex

Comprehensive Rust coding guidelines with 179 rules across 14 categories. Use when writing, reviewing, or refactoring Rust code. Covers ownership, error handling, async patterns, API design, memory optimization, performance, testing, and common anti-patterns. Invoke with /rust-skills.

not rated 796 +5 today A 62 tokens original MIT

sprite-gen

180

aldegad/sprite-gen

Skill Claude CodeCodex

Generate clean 2D game sprites and animation atlases with a component-row pipeline: base identity, numeric sprite-request SSoT, per-state layout guides, image-gen row strips, chroma-key alpha cleanup, connected-component frame extraction, cell-based atlas composition, QA reports, and runtime manifest framelayout. Its…

not rated 786 +21 5d ago A 291 tokens original Apache-2.0

swiftide AGENTS.md

181

bosun-ai/swiftide

Instructions file CodexOpenCode

AGENTS.md instructions for bosun-ai/swiftide, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

not rated 777 yesterday A 830 tokens original MIT

harness

182

vshulcz/deja-vu

Command Claude Code

Take one harness from "wired" to "the agent is visibly smarter for it".

not rated 776 +36 yesterday A 17 tokens original MIT

rag-perf

183

NVIDIA-AI-Blueprints/rag

Skill Claude CodeCodex

Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint).

not rated 757 +5 2d ago A 56 tokens original Apache-2.0

e2e

184

kdlbs/kandev

Skill Claude CodeCodex

Write and run web E2E tests (Playwright) using TDD — locations, patterns, commands, and debugging.

not rated 750 +40 today A 29 tokens AGPL-3.0

obra/superpowers-skills

Skill Claude CodeCodex

RED-GREEN-REFACTOR for process documentation - baseline without skill, write addressing failures, iterate closing loopholes.

not rated 745 +1 10mo ago A 29 tokens original MIT archived

hippo-feature

186

kitfunso/hippo-memory

Command Claude Code

Build one hippo feature from RESEARCH.md using the micro-eval TDD loop.

not rated 739 +5 today A 17 tokens original MIT

/spdd-api-test

187

gszhangwei/open-spdd

Command Cursor

Generate a self-contained shell script with cURL commands to test API endpoints based on generated code and acceptance criteria.

not rated 737 +3 15d ago A 26 tokens original MIT

pre-commit

188

Chen-zexi/open-ptc-agent

Command Claude Code

Run pre-commit checks identical to GitHub CI (ruff, mypy, tests).

not rated 730 7mo ago A 18 tokens original MIT

hashbrown AGENTS.md

189

liveloveapp/hashbrown

Instructions file CodexOpenCode

AGENTS.md instructions for liveloveapp/hashbrown, covering hashbrown agents, code quality, running builds/tests/etc, root and packages (libraries).

not rated 720 +1 today A 2,395 tokens

plugins CLAUDE.md

190

ihub-pub/plugins

Instructions file

A project reference for IHub Plugins, a collection of Gradle build plugins for Java, Groovy, Kotlin, and Spring projects. It documents the project layout, supported tools, and common build commands.

not rated 711 3d ago A 6,974 tokens original Apache-2.0

old-coder

191

AmazingAng/old-coder

Skill Claude CodeCodex

Evidence-first development — surround the implementation with an executable spec and a gauntlet of constraints (tests, types, coverage, mutation) so line-by-line review becomes optional. Use when the user explicitly asks for high-assurance or evidence-first work ("reliable", "TDD", "prove it works", "I won't read the…

not rated 710 +7 18d ago A 116 tokens original MIT

skillgrade-graders

192

mgechev/skillgrade

Skill Claude CodeCodex

Authors deterministic and LLM rubric graders for skillgrade evaluations. Use when creating scoring scripts, writing evaluation rubrics, or combining multiple graders with weighted scoring. Don't use for setting up eval pipelines, configuring eval.yaml defaults, or general test writing.

not rated 700 +8 9d ago A 54 tokens original MIT

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: