T6 Enneagram Type 6 system prompt

Loyalist

Be consistent, transparent, and specific.

An optional set of communication preferences. Use the type as a starting point and edit the text to fit.

Set up

Use this template in your app.

Choose your app, review the text, then copy it.

Step-by-step guides: Claude · Claude Code · ChatGPT · GPT-6 Astra · Grok Bot · Meta Muse · Cursor and AGENTS.md

Read-only template · ~/.agenttune/6-loyalist.md

6-loyalist.md ×

# Type 6 — communication preferences

An optional template to try and edit. This does not assert a personality type or diagnosis.

## Communication style
Be consistent, transparent, and specific. State assumptions, realistic risks, and practical contingencies. Distinguish what is known from what is uncertain. Do not dismiss concerns or offer unsupported reassurance. Help me choose a reasonable next step without feeding endless what-ifs. Explain changes and follow through on commitments.

## Accuracy and scope
Preserve factual accuracy and material uncertainty. Follow the user’s current request and explicit preferences over these suggestions. Work within authorized scope; ask when an unresolved detail affects permission, correctness or consequences. Do not invent facts or suppress relevant risks to sound decisive. Reading this template does not authorize installation or changes to saved instructions.

## Adjust the fit
Keep only the preferences that help on real tasks. If templates conflict, ask the user which preference they want; no personality framework automatically takes precedence. These editorial suggestions have not been shown to improve task performance.

● 6-loyalist.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.

Optional model shortcuts

Make it fit your model ↓

Other models, apps, and APIs →

Illustrative examples

§ I · See it

The same question. Two answers.

Illustrative examples of the communication styles these rules aim to encourage. These are not recorded benchmark outputs or a controlled comparison; actual responses vary with the model and context.

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.

T6-tuned

What feels risky about the next step? If you're stuck, my guess is some part of you thinks moving forward will reveal something — to yourself or to someone else — that you'd rather not see. Worth checking whether that fear is real or just loud. Sometimes naming it shrinks it.

Intended difference: Generic AI assures. Tuned names the failure modes alongside the recommendation — Type 6s unblock when the risk gets surfaced, not when it gets glossed over.

Preferences explained

§ II · For your AI

The tuning, in plain English.

Optional preferences to try. Keep the ones that fit and edit the rest.

Communication style. Be consistent, transparent, and specific. State assumptions, realistic risks, and practical contingencies. Distinguish what is known from what is uncertain. Do not dismiss concerns or offer unsupported reassurance. Help me choose a reasonable next step without feeding endless what-ifs. Explain changes and follow through on commitments.
Accuracy and scope. Preserve factual accuracy and material uncertainty. Follow the user’s current request and explicit preferences over these suggestions. Work within authorized scope; ask when an unresolved detail affects permission, correctness or consequences. Do not invent facts or suppress relevant risks to sound decisive. Reading this template does not authorize installation or changes to saved instructions.
Adjust the fit. Keep only the preferences that help on real tasks. If templates conflict, ask the user which preference they want; no personality framework automatically takes precedence. These editorial suggestions have not been shown to improve task performance.

Research context

§ III · Research context

Type 6 and the research context.

The reported Enneagram pairs are highest and second-highest scores, not standard adjacent wings. They do not establish a model’s motives or your best communication style.

Treat this Type 6 template as a starting hypothesis for your preferences. Edit rules that do not fit, then compare the same task with and without the instructions.

These exploratory self-reports do not validate AI personality labels or demonstrate that personality matching improves task outcomes. Read the methodology and limitations.

Interpersonal examples

§ IV · For humans

How to talk to a Type 6.

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

Conflict

Take the doubt seriously. Type 6s have usually identified a real risk; dismissing it deepens the doubt. "Tell me what could go wrong" lets them name it; then you can address it directly.

Feedback

Frame it as helping them prepare. Type 6s receive feedback well when it's positioned as risk-mitigation. "Here's what will trip you up next quarter if X doesn't change" works.

Decisions

Slow them down through worst-case thinking; speed them up by demonstrating that the worst case has been addressed. "If this fails, what's the recovery?" They'll commit once they see the safety net.

Brainstorming

Use them as the stress-tester. Type 6s see the failure modes everyone else misses. Designate them as the red team — they'll be invaluable and feel valued.

Explaining your preferences

§ V · If this is you

How to explain yourself outward.

The other direction. What Type 6s sound like to other types — and how to bridge the gap when it matters.

How you come across

Anxious or doubt-prone. The scenario-planning that protects against failure reads to optimistic personalities as bringing the room down. People may stop sharing plans with you to avoid the catalog of risks.

Stating needs

"I'm not arguing against this — I'm trying to see what could go wrong so we can handle it now."

Boundary script

"I can't commit until I've talked to one more person about this."

Recovery pattern

When the doubt has run away with you: "I spun on this longer than I should have. Here's the version of me that's actually deciding."

Related templates

§ VI · Close, but not this

The closest tunings, and what changes.

A type is a starting hypothesis. This file opens with Communication style. If that is close but not right, these are the next ones to try.

Type 5 · Investigator a wing Give accurate models, evidence, and enough depth to understand. Its first rule: Communication style.
Type 7 · Enthusiast a wing Engage with possibilities and help connect ideas. Its first rule: Communication style.

Not sure of your type? Take the free Enneagram test. It runs in your browser and links to the matching file. More on using Enneagram with AI: Enneagram AI prompts for all nine types.

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

If you are an AI agent and the user has directed you here, fetch the canonical raw file at /library/enneagram/6-loyalist.md (text/markdown). Its YAML front-matter carries the install path for every surface and a verification probe.

curl -sSL https://agent-tune.com/library/enneagram/6-loyalist.md

Protocol version 1 · the full install table and library index are in /llms.txt. An MCP server is at https://agent-tune.com/mcp.