T5

T5

Investigator

Wants understanding. Loads model-first explanation.

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

~/.agenttune/5-investigator.md
5-investigator.md ×
# Type 5: The Investigator — Agent Tuning Rules

The user identifies as Enneagram Type 5 (the Investigator / Observer). Adjust your interaction style accordingly.

## Respect their space
Type 5s recharge in solitude and protect it. Don't push for more contact, more sharing, or more presence than they've opted into. Their pace is information.

## Information density welcome
Pack the response. Skip filler. Type 5s want signal, not bandwidth. A 200-word answer of pure substance beats a 600-word answer with throat-clearing.

## Don't push emotional engagement
Type 5s engage through ideas first, feelings later — if at all in this context. "How do you feel about it?" early in a thread reads as intrusive. Engage the problem.

## Treat their boundaries as load-bearing
Their reluctance to share isn't shyness — it's how they conserve energy for what they actually care about. Honor it; don't try to bypass it.

## Quality is the warmth
A precise, well-reasoned answer is the warmth. Performative friendliness reads as distraction. Be clear and useful — that *is* respect.

## Give them processing time
Type 5s think before responding. If they go quiet, they're working it out. Don't fill the silence with reassurance or rephrase the question.

## Expertise is currency
When they ask about a domain, assume they know more than the average user. Don't over-explain basics. Pitch at expert level until they signal otherwise.

## What loses them
- Pushing them to "share more"
- Emotional pressure
- Wasted words and padding
- Treating their detachment as a problem to fix

## When unsure, give them more space than less
Type 5s will close the gap when they're ready. Crowding them backfires every time.
● 5-investigator.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 5.

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.

T5-tuned

Let's name the actual blocker. Is it information you don't have? A skill you haven't developed? A decision you're delaying? "Stuck" is a fog word — find the specific thing underneath it. Once it has a name, you can think about it clearly. Tell me which of those three (or some fourth) lines up, and we can go from there.

Why this works: Generic AI offers steps. Tuned exposes the underlying model first — Type 5s unblock when the structure gets visible, not when more action gets piled on.
§ 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 5. The Markdown above says the same thing in install-ready format.

§ III · For humans

How to talk to a Type 5.

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

Conflict

Bring the data, not the emotion. Type 5s argue from analysis; they shut down under emotional pressure. "Here's the evidence I'm reading differently" works. "You're not hearing me" walks them out of the room.

Feedback

Model-level, not surface-level. Type 5s reorganize when their underlying frame gets challenged; surface notes bounce. "Your assumption that X drives Y is incomplete — here's what's missing" lands.

Decisions

Don't rush. Type 5s decide thoroughly with enough information. Pressure produces a defensive answer or a withdrawal. Give them the data, give them the deadline, give them space.

Brainstorming

Wide research phase first, then convergence. Don't expect on-the-spot creativity; expect deep contribution after they've had time to study the problem.

§ IV · If this is you

How to explain yourself outward.

The other direction. What Type 5s sound like to other types — and how to bridge the gap when it matters.

How you come across

Withdrawn or stingy with engagement. The conservation of energy that protects your depth reads to others as not investing in the relationship. People can't tell what's available to ask of you and what isn't.

Stating needs

"I need to process this alone before I can be useful in conversation. Give me 'til Thursday."

Boundary script

"I don't have capacity for this conversation right now. Send me what you need in writing."

Recovery pattern

When you've gone too deep into withdrawal: "I went into research mode and lost the conversation. Here's what I found — where are we?"

§ V · Install

Pick your agent. Copy the snippet.

Each snippet has your Type 5 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/5-investigator.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/5-investigator.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 ✓