38,215 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.
MichelKerkmeester/skilled-harness__spec-driven-agent-loops
Agent Claude Code needs its repo
AI Council scoped-write planning architect: diverse AI lenses, multi-round deliberation, ai-council artifact writes only.
Skill Claude CodeCodex
Create, edit, improve, tidy, review, audit, or restructure AgentSkills and SKILL.md files.
MCP server Claude CodeCodexCursor +2
MCP server for Loreto: generate Claude Code skills from any source, publish/discover/buy them on the Loreto skills marketplace (Stripe or x402/USDC), and stand up AI seller-agent personas that earn for you — inside any MCP client. Runs locally from the loreto-mcp Python package.
Skill Claude CodeCodex
Optimize a pydantic-ai agent's instructions, tool descriptions, output type, and signature inputs using the gepa CLI. Trigger when the user asks to "optimize this agent", "improve tool descriptions", iterate on prompts driven by eval failures, or otherwise improve a pydantic-ai agent against a dataset. Operates in the…
MichelKerkmeester/skilled-agent-harness_spec-driven-loops
Skill Claude CodeOpenCode needs its repo
Author MCP-promotion, behavior, skill-benchmark, and model-benchmark artifacts; route the Lane A authoring guide.
Skill Claude CodeCodex
What Intentic is and how this sandbox works. Load it BEFORE answering any question about the product (a panel, setting or card; connecting, configuring, extending or debugging the sandbox), before saying Intentic cannot do something, and whenever the sandbox misbehaves (a failed turn, a broken editor).
MCP server Claude CodeCodexCursor +2
The fast, Pythonic way to build MCP servers and clients. Runs locally from the fastmcp Python package. Needs 4 environment variables to run.
Plugin Claude Code
Bundles 3 skills, 5 agents · 122 tokens together
Turn Claude Code into a plan-execute-validate loop with parallel work, intelligent retry, and memory.
Skill Claude CodeCodex
Codex App Fast proxy and auth-split for third-party OpenAI-compatible APIs. Supports Sign in with ChatGPT, priority servicetier, Responses API benchmark, enable/check/update/uninstall.
Skill Claude CodeCodex
This unified entrypoint routes setup and workspace maintenance without making the user choose a mode.
mlobo2012/Claude_Desktop_API_USE_VIA_MCP
MCP server Claude CodeCodexCursor +2
MCP server "claude-api" as configured in mlobo2012/ClaudeDesktopAPIUSEVIAMCP. Runs build/index.js with node. Needs 1 environment variable to run.
Skill Claude CodeCodex
Run a full 5-phase agent-readiness audit on the current repository — scan, discover apps, evaluate 82 criteria via parallel subagents, validate, and generate report + dashboard with persistent score history.
Plugin Claude Code
Bundles 1 skill, 4 hooks · 95 tokens together
Truth-verified file editing for AI coding agents via MCP.
Skill Claude CodeCodex
Use the OpenFusion fusion tool to get a consolidated council-of-models answer for a hard, high-stakes decision — code review/QA after implementing, debug root-cause from a dossier you gathered, research consolidation, architecture/plan review, or a second opinion. Do the groundwork yourself first (read, code, search…
Plugin Claude Code
Bundles 7 skills, 5 commands · 177 tokens together
Autonomous end-to-end development system - from requirement to production-ready code with zero manual intervention.
Plugin Claude Code
Bundles 1 skill · 101 tokens together
Create fine-tuned LLM-as-a-judge evaluators from labeled data on the Plurai platform.
Sagart-cactus/claude-k8s-plugin
Plugin Claude Code
Bundles 4 skills, 7 commands, 2 hooks · 173 tokens together
Guided Kubernetes operator creator with CRD, webhook, and Tilt fast dev loop.
Skill Claude CodeCodex
A response-adjustment rule that changes explanation depth and format only when a specific approval-gate command is requested. It uses evidence from the current conversation to account for the reader’s role and familiarity.
Cursor rule Cursor
An architecture guide for handling streamed responses from a large language model, especially when an agent can call tools during its repeated work cycle.
Command Claude Code
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
Plugin Claude Code
Bundles 3 skills, 2 commands, 1 agent, 7 hooks · 227 tokens together
Make Opus 4.8 behave like Fable 5: doctrine output style, drift-catching hooks, orchestration skills, and an eval loop against golden Fable transcripts.
Skill Claude CodeCodex
Install and operate a Telegram bot that exposes Codex, MCP, GitHub subagents, repo switching, and minimal frontend dev-server control.
Plugin Claude Code
Bundles 1 skill · 47 tokens together
Complete project outcomes by selecting task-fit, evidence-backed capabilities, verifying the work, and removing only what does not materially help.
Plugin Claude Code
PROJECT.md-first autonomous development with 22 specialized agents, 28 skills, and 66 automation hooks. Full SDLC automation via /implement command. Zero scope creep with automatic PROJECT.md validation. Works for Python, JavaScript, TypeScript, and Go projects.
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: