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.
Skill Codex
Route human-in-the-loop checkpoints through Turn MCP Web by calling turn.wait (aliases: turnwait, turn). Use when an agent has access to the Turn MCP server and must pause for approvals, clarifications, branch choices, or operator handoffs without ending the current run.
systempromptio/systemprompt-template
Skill Claude CodeCodex
Drive every stage of the governance pipeline end to end, then prove that each decision was audited. This is the guided tour of the enforcement spine: the same four stages run on every tool call in the workspace.
Plugin Claude Code
Bundles 1 skill · 48 tokens together
Two frontier models, one job each. Claude plans and reviews; GPT-5.6 Sol writes the code via Codex CLI. The model that wrote the diff never grades it.
Skill Claude CodeCodex
Use when building, migrating, or debugging Agent Evals on Inngest: scoring AI agent or workflow outcomes, deferred scorers, sessions, traces, step experiments, experiment variant attribution, Insights queries, or production eval loops for prompts, models, tools, providers, and agent behavior. Covers TypeScript SDK v4…
Plugin Claude Code
Bundles 4 skills, 9 commands, 5 hooks · 159 tokens together
Persistent memory system for AI coding assistants. Captures decisions, learnings, and context from coding sessions and surfaces them when relevant.
fabio-barboza/development-orchestrator
Skill Claude CodeCodex
Initializes the project, identifies relevant skills, and updates the project configuration file (CLAUDE.md, .github/copilot-instructions.md, .cursor/rules/project.mdc, or .cursorrules) with project summary, conventions, and available skills. Accepts an optional argument "agents" to only install orchestration agents…
Plugin Claude Code
Bundles 12 commands · 125 tokens together
Trace analysis and context remediation for AI agents.
gensecaihq/MCP-Developer-SubAgent
Agent Claude Code
MCP troubleshooting and debugging specialist for protocol issues, transport problems, and diagnostic analysis.
bejranonda/LLM-Autonomous-Agent-Plugin-for-Claude
Plugin Claude Code
Bundles 27 skills, 1 command, 36 agents · 1,556 tokens together
Four-tier autonomous agent architecture with specialized agents, skills, and commands for code analysis, quality control, pattern learning, and automated validation.
Plugin Claude Code
Bundles 3 skills, 1 agent, 1 hook · 288 tokens together
Auto-converge a Claude-written plan via Codex (gpt-5) review iterations until clean ALLOW or max-iter.
MCP server Claude CodeCodexCursor +2
MCP server "a2a-client-mcp-server" as configured in tesla0225/mcp-a2a. Runs locally from the a2a-client-mcp-server npm package.
Skill Claude Code
An evaluation framework for testing coding agents against defined benchmarks, or repeatable tests used to compare results.
Plugin Claude Code
Bundles 11 skills, 1 agent, 3 hooks, 5 MCP servers · 1,985 tokens together
ERPAVal — autonomous software development workflow for Claude Code. Comprehensive standalone bundle: the erpaval workflow plus 10 vendored companion skills (product-discovery, research, ultraplan, tech-stack-builder, product-strategy, working-backwards, customer-research, meta-prompt-optimizer, product-design-shared…
Skill Claude CodeCodex
Turn a video, tutorial, playlist, or course into an installed, evidence-grounded course Skill that can teach, give practice and feedback, apply demonstrated methods, and answer reference questions. Use when the user provides video sources and wants reusable learning or operational capability.
Plugin Claude Code
Bundles 32 skills, 5 agents, 2 hooks · 2,614 tokens together
OneBrain — Your AI Thinking Partner.
Skill Claude CodeCodex ⚠ unsafe
A framework for giving an agent awareness of its activity, attention, timing, and repeated behaviour. It also combines memory scoring, safety handling for untrusted data, decision guidance, focus tracking, and tool-use records.
Skill Codex needs its repo
A skill that recommends which already-installed local agent skill matches a described task. It uses the machine's skill catalogue and does not perform the task itself.
Plugin Claude Code
Bundles 1 skill · 110 tokens together
Run and manage long-lived coding agents in a neosh workspace: start conversations in any directory or worktree, fan work out across many at once, watch and steer them, collect what they produced.
Agent Claude Code
Design and plan application architecture using MCP tools.
Plugin Claude Code
Bundles 1 skill · 0 tokens together
Integrate the Vouch Protocol: cryptographic identity and accountability for autonomous AI agents. Signing and verifying agent actions, did:web and did:key, Data Integrity proofs, the post-quantum proof set, delegation chains, and revocation, across SDKs on every major platform.
Skill Claude CodeCodex
The prompt engineer for autonomous agent runs. Interviews the user about what they're building, then writes the perfect mission prompt — never-ask autonomy rules, multi-agent orchestration, end-to-end UI testing quality bar, and a provable definition of done baked in — plus a full overnight scaffold (feature list…
Skill Codex
Use when the user explicitly invokes $fable-mode or asks for fable-mode style routing. Keep ordinary simple tasks outside this skill; it is for intent, output-form, grounding, capability, and depth control.
Skill Claude CodeCodex
Eino LLM/AI application development framework assistant (Golang). Use when the user needs to: (1) Build AI agents, (2) Create LLM applications, (3) Implement tool calling, (4) Build multi-agent systems, (5) Create workflows with Graph/Compose, (6) Implement streaming, (7) Human-in-the-loop patterns, or any other Eino…
Plugin Claude Code
Bundles 13 skills, 2 MCP servers · 818 tokens together
Graph-first governance workflow guard for Aming Claw. Bundles one onboard-first skill entrypoint and the project MCP server (.mcp.json) so Claude Code sessions start from MCP onboardrouteguide, with HTTP fallback only when MCP is unavailable, before selecting role, work type, runtime contract, worker, QA, or system o.
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: