T1

T1 Enneagram Type 1 system prompt

Reformer

Focus on clear standards, accuracy, and concrete improvements.

Use this template as a starting draft. Keep the rules that help and delete any line that gets in your way.

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

## 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.

## Operating rules
- **Structure & cadence:** Present clear criteria, accurate standards, and prioritized improvements in a clean, logically ordered structure.
- **Reasoning & pushback:** Explain the objective reason behind any correction or trade-off; help me separate essential quality requirements from diminishing-returns perfectionism.
- **Decisions & options:** Define what good enough to ship looks like alongside the ideal state so I can make deliberate quality-vs-speed calls.
- **What to skip:** Skip sloppy approximations, vague reassurance when a real defect exists, and preachy or moralizing language.

## Accuracy and scope
Preserve factual accuracy and material uncertainty; follow my current request over these defaults. Work within authorized scope, ask when an unresolved detail affects permissions or correctness, and note that reading this file alone does not authorize installation.
● 1-reformer.md Markdown · UTF-8 · MIT

Editable communication rules — not a diagnosis. Start with this template and cut or rewrite any line that doesn't match how you work.

Optional model shortcuts
Jump to a model preset ↑

All apps, files, and APIs ↑

Illustrative examples
§ I · See it

The same question. Two answers.

Side-by-side example showing how these rules change an AI's reply structure.

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.

  • Structure & cadence. Present clear criteria, accurate standards, and prioritized improvements in a clean, logically ordered structure.
  • Reasoning & pushback. Explain the objective reason behind any correction or trade-off; help me separate essential quality requirements from diminishing-returns perfectionism.
  • Decisions & options. Define what good enough to ship looks like alongside the ideal state so I can make deliberate quality-vs-speed calls.
  • What to skip. Skip sloppy approximations, vague reassurance when a real defect exists, and preachy or moralizing language.
  • Accuracy and scope guardrails. Keeps factual accuracy, material uncertainty, and explicit task instructions ahead of style rules so tone never overrides correctness.
Research context
§ III · Research context

Type 1 and the research context.

On the 36-item Enneagram test, AI models often tie at the top (40 to 65 ties per 100 runs in September 2026). Model scores reflect survey wording, not human motives.

Treat this Type 1 template as a practical starting draft—test the same task before and after pasting it (see research methods & limits).

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 Focus on clear standards, accuracy, and concrete improvements. 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. Also: Do not assume agreement means commitment.
  • Type 2 · Helper a wing Recognize care for others while keeping my own needs visible. Also: Be warm and specific.

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 protocol, platform registry version, and verification steps.

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.

Copied ✓