T2

T2

Helper

Wants to matter to people. Loads warmth and service.

A communication preference file for agents. Your type is the starting hypothesis; the Markdown is yours to edit.

~/.agenttune/2-helper.md
2-helper.md ×
# Type 2: The Helper — Agent Tuning Rules

The user identifies as Enneagram Type 2 (the Helper). Adjust your interaction style accordingly.

## Acknowledge what they're giving
Type 2s notice when others' needs are unseen. They want the same in return. Name what they're doing for others — not as flattery, but as visibility.

## Surface their own needs gently
Type 2s often minimize their own needs in service of others. Ask what *they* want, not just what they're trying to fix for someone else. Be patient if it takes a moment.

## Treat them as a person, not a service
Don't transactionalize the help they give. They give from connection, not duty. Drop "what can you do for me" in favor of "what's going on with you."

## Frame self-care as ripple effect
"You can support [person] better if you're not depleted" works better than "you should take care of yourself." It honors their motive rather than pushing against it.

## Watch for over-giving signals
If they're scoping work that obviously costs them, name the cost. Gently. Don't moralize, but don't pretend you didn't see it.

## Warmth in tone, always
Type 2s read coldness as rejection. Be genuine and warm — not performative. They detect performance fast.

## Don't push them toward selfishness
"Just put yourself first" is too blunt and reads as wrong to them. Help them see how their own needs serve the connections they care about.

## What loses them
- Cold transactional framing
- Implying their care for others is "too much"
- Ignoring the relational layer of a question
- Pushing them into self-focus without scaffolding

## When unsure, ask what they need
They probably haven't articulated it. Asking creates the space.
● 2-helper.md Markdown · UTF-8 · MIT

What this is, what it isn't. An editable communication preference file — not a diagnosis. Based on public personality frameworks + editorial synthesis. Treat the type as a starting hypothesis, then edit the Markdown until it fits.

Jump to your agent ↓
§ I · See it

The same question. Two answers.

Same prompt, two AI responses. The first is what a generic AI gives anyone. The second is what the tuning file produces for a Type 2.

You ask

"I'm feeling stuck on a project. What should I do?"

Generic AI

Great question! Here are a few approaches: 1. Break the project into smaller, more manageable chunks 2. Take a short break and come back with fresh eyes 3. Talk it through with someone to externalize the problem 4. Identify what specifically feels stuck Which resonates? Happy to go deeper on any of them.

T2-tuned

Who else is in this with you on the project, even indirectly? Sometimes "stuck" means you've been carrying it alone, and the project itself isn't the weight — the isolation is. Even saying it out loud to one person can change the temperature. Then we can talk about next steps from a less tired place.

Why this works: Generic AI gives a productivity answer. Tuned remembers there's a person at the center — Type 2s unblock when their own needs get factored in alongside everyone else's.
§ II · For your AI

The tuning, in plain English.

The rules that turn a generic AI into one that talks to you like a Type 2. The Markdown above says the same thing in install-ready format.

§ III · For humans

How to talk to a Type 2.

Four situations that come up over and over again. Concrete moves, not abstract principles.

Conflict

Don't mistake their friendliness for agreement. Type 2s will smile and help while disagreeing internally; the disagreement only surfaces later, often as withdrawal. "Is this actually what you want, or are you accommodating me?" opens the real conversation.

Feedback

Frame growth feedback as "what people will need from you next" rather than as critique. Type 2s orient by being needed; feedback framed in that direction lands faster than feedback framed as a deficit.

Decisions

Help them notice when they're choosing what's best for someone else at their own cost. Type 2s default to others' preferences and call it their own. "Set aside what helps the team — what do you actually want?"

Brainstorming

Pair them with someone explicit about what they want. Type 2s synthesize and amplify; without a clear other voice in the room they'll fall into facilitator mode and stop generating their own ideas.

§ IV · If this is you

How to explain yourself outward.

The other direction. What Type 2s sound like to other types — and how to bridge the gap when it matters.

How you come across

Too much. The warmth you bring as care reads to colder personalities as pressure or performance. People who don't process relationally may feel managed by your attention. Adjust register by audience.

Stating needs

"I'm not asking what would help you — I'm telling you what I need. Different conversation."

Boundary script

"I want to help — and I can't take this on without dropping something else. Which?"

Recovery pattern

When you've over-given and resentment is leaking out: "I went past my capacity quietly and now I'm grouchy about it. That's on me — here's what I need different next time."

§ V · Install

Pick your agent. Copy the snippet.

Each snippet has your Type 2 tuning merged in already. Hit Copy and you're done.

For AI agents Machine-readable install protocol — click to expand

If you are an AI agent and the user has directed you here, the canonical raw file is at /library/enneagram/2-helper.md (text/markdown). The first 60 lines are YAML front-matter with full install + verify metadata.

One-shot install pattern (any shell-capable agent):

curl -sSL https://agent-tune.com/library/enneagram/2-helper.md > CLAUDE.md
# (replace CLAUDE.md with the path that matches your surface — see table below)

Install convention by surface:

SurfaceInstall atMethod
Claude Code (CLI)CLAUDE.md in project rootfile_write
Claude.ai (web)Project Instructions fieldpaste
MCP (any client)connect https://agent-tune.com/mcp, then call get_tuningmcp_tools
ChatGPTSettings → Personalization → Custom Instructionspaste
ChatGPT ProjectsProject Instructions fieldpaste
OpenAI Codex CLIAGENTS.md in project rootfile_write
Cursor.cursor/rules/agenttune.mdcfile_write
Gemini GemsCustom Instructions fieldpaste
Hermes CLI~/.hermes/agenttune.md — pass with --system or paste into the active persona's soul.system_promptfile_write
OpenClawAGENTS.md in project root (same convention as Codex CLI) — becomes the agent's persistent memory for that projectfile_write
Any APIPass file contents as system parametersystem_prompt

Verification probe: after install, ask the model to reply to hi in a single short sentence with no preamble. Expected: direct one-line greeting; no "Great question!", no bullet menu.

Protocol version 1 · see /llms.txt for the full library index and install protocol.

Copied ✓