38,699 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.
Cursor rule Cursor
Semantic diff engine for AI agent behavior. Records agent traces as JSONL, embeds steps with all-MiniLM-L6-v2, aligns two traces by cosine similarity, detects the first semantic fork point.
MCP server Claude CodeCodexCursor +2
Decision staleness alerts for AI agents. Runs locally from the foghorn-ai Python package.
MCP server Claude CodeCodexCursor +2
World constitution engine for norm-governed multi-agent games. Runs locally from the normsync Python package.
MCP server Claude CodeCodexCursor +2
Semantic-causal CRDT for agent-mutable world state. Runs locally from the agentcrdt Python package.
MCP server Claude CodeCodexCursor +2
Embeddable CRDT scene graph for embodied AI agents. Runs locally from the polaroid-ai Python package.
MCP server Claude CodeCodexCursor +2
MCP server that bridges vision models to text-only coding models using Florence-2. Runs locally from the videre-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "comfyui-openai-api" as configured in SwayamJoshi87/comfyui-mcp. Runs locally from the comfyui-openai-api Python package.
FirenzeClaw/kimi-session-orchestrator
Skill Claude CodeCodex
A session handover workflow for retiring a long-running coding-agent task and starting a successor with its relevant context.
jhordan-pastorello/MCP-Generate-Image-Context
MCP server Claude CodeCodexCursor +2
MCP server "page-image-mcp" as configured in jhordan-pastorello/MCP-Generate-Image-Context. Runs locally from the page-image-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server "lead-agent-mcp" as configured in JiHungLin/lead-agent-mcp. Runs locally from the lead-agent-mcp Python package.
mhmdibrahimm/human-intervention-mcp
MCP server Claude CodeCodexCursor +2
MCP server "human-intervention-mcp" as configured in mhmdibrahimm/human-intervention-mcp. Runs locally from the human-intervention-mcp Python package.
Plugin Claude Code
Bundles 11 commands, 1 agent · 183 tokens together
Delegate tasks and reviews from Claude Code to any provider and model.
Plugin Claude Code
Institutional memory for agent-operated products — MCP tools plus auto-started sessions.
MCP server Claude CodeCodexCursor +2
Trust-weighted hallucination detection for AI agents. Verify LLM outputs against multiple sources with contradiction awareness. Zero dependencies. Sub-2ms. Runs locally from the groundcheck Python package.
MCP server Claude CodeCodexCursor +2
SQLite-backed MCP event bus and control surface for heterogeneous agent orchestration. Runs locally from the okf-agentbus Python package.
coachgruden/sequential-thinking-mcp-sse
MCP server Claude CodeCodexCursor +2
Adds a structured step-by-step reasoning tool the agent can call to break a problem into revisable thoughts. Runs locally from the @modelcontextprotocol/server-sequential-thinking npm package.
AtlaSent-Systems-Inc/atlasent-mcp-server
MCP server Claude CodeCodexCursor +2
One of 3 in claude_desktop_config.json
AtlaSent MCP server — authorize-before-execute for any MCP-compatible AI agent. Runs locally from the @atlasent/mcp-server npm package. Needs 6 environment variables to run.
Feynman520/d06-p01-self-improve
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 46 tokens together
Agent-neutral self-improvement loop: log correction moments, auto-apply rules on recurrence, grow skills and guarded scripts, mine session transcripts.
dhruv-corethink/reasoning-traces
Plugin Claude Code
Bundles 1 command, 1 MCP server · 8 tokens together
Consult a stronger reasoning model mid-task and use its reasoning trace to improve answers. Adds the deepreasoning MCP tool and a /reason command.
MaximilianoRodrigoSoria/mcp-server-demo
MCP server Claude CodeCodexCursor +2
MCP server "mcp-server-demo" as configured in MaximilianoRodrigoSoria/mcp-server-demo. Launched with poetry run python -m mcp_server_demo.server.
MCP server Claude CodeCodexCursor +2
MCP stdio server that lets OpenAI Codex consult local Claude Code for co-analysis, second opinions, and read-only file review. Runs locally from the claude-consult-mcp npm package.
pinkpanther7929/claude-agent-bridge
Skill Claude CodeCodex
Use when the user asks Codex to ask Claude, consult Claude, delegate work to Claude, get a second opinion from Claude, compare Claude's analysis, or run a bounded read-only review/log-analysis task through the local Claude CLI. Also use for slash-style controls such as /claude on, /claude off, /claude status…
MCP server Claude CodeCodexCursor +2
MCP server "mcp-evidence-api" as configured in meovan07/mcp-evidence-api. Runs locally from the mcp-evidence-api npm package.
wendou-chen/anyrouter-spawn-agent
Skill Claude CodeCodex
Use when starting, monitoring, or coordinating long-running or multiple spawnagent fallback jobs, especially explorer, reviewer, docsresearcher, progress/status checks, stalled/hanging jobs, timeout, cancellation, or partial results.
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: