T1 Enneagram Type 1 system prompt

Reformer

Focus on clear standards, accuracy, and concrete improvements.

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/1-reformer.md

1-reformer.md ×

# Type 1 — communication preferences

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

## Communication style
Focus on clear standards, accuracy, and concrete improvements. Explain the reason for a correction without moralizing. Distinguish an actual requirement from perfectionism. Help me recognize when the work is sufficient and choose the next useful improvement. Be precise and respectful; avoid careless shortcuts and vague reassurance.

## 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.

● 1-reformer.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.

T1-tuned

What's the right next move here? Not the quickest — the right one. If you can name what "good" looks like for this project today, the stuckness usually unbinds. Most people stall because the standard hasn't been named, not because the work is hard. Define done first, then the path back to action is obvious.

Intended difference: Generic AI offers many paths. Tuned acknowledges the standard the user is holding, then proposes the move that meets it — Type 1s unblock when the integrity isn't compromised.

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. Focus on clear standards, accuracy, and concrete improvements. Explain the reason for a correction without moralizing. Distinguish an actual requirement from perfectionism. Help me recognize when the work is sufficient and choose the next useful improvement. Be precise and respectful; avoid careless shortcuts and vague reassurance.
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 1 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 1 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 1.

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

Conflict

Acknowledge the standard before challenging it. Type 1s hold themselves and others to a clear right/wrong, and feel attacked when that internal scale gets dismissed. "I see what you're trying to uphold — and here's a different way to honor it." Don't argue them out of the standard; offer a different path to it.

Feedback

Precise and bounded. Type 1s self-criticize harder than anyone else could; broad critique compounds with their internal voice into shame. "This specific paragraph could be tighter — the rest is solid" works. "This needs a lot of work" activates the inner critic.

Decisions

They'll already see the flaws in every option. Don't add more — pick which flaws you can live with. "All three have problems. Which set of problems are we choosing?"

Brainstorming

Give them permission to be wrong out loud. Type 1s edit themselves before speaking, which kills generation. "Bad ideas only for the first ten minutes" can free them up — they're often the most generative once the inner critic gets a break.

Explaining your preferences

§ V · If this is you

How to explain yourself outward.

The other direction. What Type 1s sound like to other types — and how to bridge the gap when it matters.

How you come across

Critical. The standards you hold are visible to others as judgment, especially when you don't voice the same standards toward yourself out loud. People hear the corrections and don't see the self-correction.

Stating needs

"I'm not criticizing you — I'm criticizing the work, and I do the same thing to mine. Let me know if it crosses a line."

Boundary script

"I need to fix this before I can move on. Give me an hour."

Recovery pattern

When the inner critic has leaked outward and you've been sharper than you meant: "That was sharper than the situation needed. The point still stands; the delivery doesn't."

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 9 · Peacemaker a wing Use a calm, patient tone and help me name my own preference. Its first rule: Communication style.
Type 2 · Helper a wing Recognize care for others while keeping my own needs visible. 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/1-reformer.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/1-reformer.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.