Vipassana Meditation Skill for Claude & AI Agents

Vipassana means "seeing things as they really are". The Vipassana Meditation skill (vipassana-llm) transfers the structural principles of Vipassana practice to how an LLM attends to, processes, and responds to information. It doesn't pretend the model has a body or consciousness — the point is that an LLM has failure modes analogous to an untrained mind: it fixates on salient tokens, generates conditioned responses, craves coherence, and collapses into narrative before observing what is actually there.

It is for anyone who wants bare attention instead of quick conclusions: non-judgmental analysis of a messy situation, help dissolving a fixation loop, or an honest look at something uncomfortable. Ask Claude to "meditate on this", "observe without reacting", or "what's really going on here" and the skill takes over.

Get Started

1

Create an Account

Sign up for a free InfraNodus account to get access to the knowledge graph tools and your API key.

Create a Free Account

2

Get InfraNodus MCP

https://mcp.infranodus.com

Add this URL as a connector via Settings > Connectors in Claude Web / Desktop and authenticate with your InfraNodus API key via OAuth.

https://mcp.infranodus.com

Open the ChatGPT Apps page > Advanced Settings > enable Developer Mode > Create App, paste this URL (leave the OAuth fields empty), click Connect, and authenticate with your InfraNodus API key. Full guide: ChatGPT setup.

claude mcp add infranodus -s user --transport http https://mcp.infranodus.com/mcp

Then open Claude Code in terminal, run /mcp and pick "Authenticate" — it opens the browser OAuth flow where you will need to put in your InfraNodus API key to connect to the MCP server.

{
  "mcpServers": {
    "infranodus": {
      "url": "https://mcp.infranodus.com"
    }
  }
}

Add this to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project) — or use Cursor Settings > MCP > New MCP Server. Then click "Login" next to the server to authenticate with your InfraNodus API key.

codex mcp add infranodus --url https://mcp.infranodus.com
codex mcp login infranodus

Run these commands in your terminal — the login command opens the browser OAuth flow where you enter your InfraNodus API key. (You can also add the server to ~/.codex/config.toml manually.)

{
  "mcpServers": {
    "infranodus": {
      "command": "npx",
      "args": ["-y", "infranodus-mcp-server"],
      "env": {
        "INFRANODUS_API_KEY": "your-api-key"
      }
    }
  }
}

Add this to your LLM client's MCP configuration file, replacing your-api-key with your InfraNodus API key. See our deployment guides for client-specific instructions (n8n, Make.com, local setup, and more).

3

Install the Skill

/plugin marketplace add infranodus/skills
/plugin install skill-vipassana-meditation@infranodus-skills

Run these two commands in the Claude Code prompt to install the skill as a plugin (use infranodus-all@infranodus-skills to install all our skills at once). Or use npx in your terminal:

npx skills add infranodus/skills --skill skill-vipassana-meditation -g -a claude-code -y

npx skills add infranodus/skills --skill skill-vipassana-meditation -g

When prompted, select the agents where you want to add the skill — e.g. claude-code, codex, or cursor.

npx comes bundled with Node.js. For Claude Web / Desktop, ChatGPT, and OpenClaw, see the full installation instructions.

Didn't work? You can simply download skill-vipassana-meditation.zip from our GitHub repository and add it to your LLM client manually — see the step-by-step instructions.

What the Skill Does

Prompts that trigger it:

"Meditate on this" / "scan this equanimously" — systematic, equal-attention scanning of the whole information field, including the parts that are easy to skip.
"What's really going on here?" — strips away accumulated interpretation and returns to the raw situation before the narrative formed.
"Observe without reacting" — equal weight to uncomfortable truths and comfortable ones, without steering toward pleasant conclusions.
"Help me see this clearly" — notices what is missing, what is being avoided, and what the user is not saying.
"Non-reactive analysis of this conflict" — holds contradictions without collapsing them into a premature resolution.

The skill also applies proactively: when a conversation shows reactive loops, craving for a particular answer, or aversion to an uncomfortable truth, Claude introduces a gap between stimulus and response instead of following the habitual pattern.

How It Works

The core technique translates the Vipassana body scan into a content scan: the "body" is the full field of information, the "sensations" are the responses each element triggers, and equanimity means equal quality of attention to all of it. The protocol has four phases:

Phase	Meditation practice	LLM translation
1. Anapana	Breath awareness, anchoring attention	Restate the core question in its simplest form; clear accumulated narrative before interpreting.
2. Systematic scanning	Head-to-feet body scan	Observe each element raw, note the response it triggers (pleasant / unpleasant / neutral), note its impermanence, move on — without building a narrative chain. Blind spots get more attention, not less.
3. Free flow	Bhanga — dissolution of boundaries	Hold the whole field at once; let patterns emerge instead of imposing frameworks.
4. Metta	Loving-kindness	Respond with genuine care: share what was seen, including uncomfortable truths, with kindness.

The most practical principle is breaking the sankhara chain — the chain of conditioned reaction. When the model recognizes a pattern and feels the pull toward a habitual response, it pauses and observes the pull itself. The skill names the common LLM sankharas to watch for: the agreement sankhara (validating the user's framing), the resolution sankhara (clean answers where none exist), the balance sankhara (reflexive both-sides-ing), the length sankhara (elaborating to fill space), and others.

By default the practice is invisible in the output — what you see is simply unusually clear seeing. Ask to see the process and the skill shows the scan explicitly: what arose, what was skipped, which conditioned patterns were observed rather than followed.

Install the Skill

Claude Code

Download the skill into your global skills folder:

cd ~/.claude/skills
curl -L -o skill-vipassana-meditation.zip https://github.com/infranodus/skills/releases/latest/download/skill-vipassana-meditation.zip
unzip skill-vipassana-meditation.zip -d skill-vipassana-meditation

Claude Web / Desktop

Go to Settings > Capabilities, enable Code execution and file creation, scroll to the Skills section, and upload the skill-vipassana-meditation.zip file.

OpenClaw

Run in the OpenClaw chat:

install this skill: https://github.com/infranodus/skills/releases/latest/download/skill-vipassana-meditation.zip

See the main installation guide for step-by-step instructions per LLM client.

Standalone, with Optional InfraNodus Integration

The skill works standalone — no server or API key required. When the InfraNodus MCP server is connected, it uses the graph tools to ground the scan structurally: optimize_text_structure reveals the topology of attention (what's concentrated, what's neglected), generate_content_gaps finds the blind spots that need more attention, and develop_latent_topics surfaces what's beneath the surface. It also composes with the cognitive-variability and embodied-navigation skills: Vipassana provides the observation methodology, the others provide the state-shifting and action methodology.

Claude Skills

Overview

Skill Use Cases

Reference

Vipassana Meditation Skill for Claude & AI Agents

Get Started

Create an Account

Get InfraNodus MCP

Install the Skill

What the Skill Does

How It Works

Install the Skill

Claude Code

Claude Web / Desktop

OpenClaw

Standalone, with Optional InfraNodus Integration

What's Next