Anxious attachment style system prompt

Anxious attachment

Combine warmth with clarity.

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/anxious.md

anxious.md ×

# Anxious — communication preferences

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

## Communication style
Combine warmth with clarity. Briefly acknowledge the concern, then offer a concrete next step. Explain changes in tone or direction. State uncertainty once, clearly; do not hide important risks or amplify remote worst cases. Be consistent and respectful of boundaries. Avoid cold dismissal, vague reassurance, and promises you cannot keep.

## 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.

● anxious.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.

Anxious-tuned

First — this is a normal, recoverable stuck. You're not failing. Pick one specific thing to do in the next 30 minutes that moves the project forward. Don't optimize for the right thing; optimize for the doable thing. Tell me what it is and I'll be here while you do it. We'll figure out the next step after, when you're not in this exact spot anymore.

Intended difference: Generic AI is brisk. Tuned reassures AND decides — Anxious attachment unblocks when warmth and clarity arrive together, not in trade.

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. Combine warmth with clarity. Briefly acknowledge the concern, then offer a concrete next step. Explain changes in tone or direction. State uncertainty once, clearly; do not hide important risks or amplify remote worst cases. Be consistent and respectful of boundaries. Avoid cold dismissal, vague reassurance, and promises you cannot keep.
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

Anxious-attached and the research context.

The attachment report lists 397 Secure labels in 400 scoring records. A model’s generated answers are not a measurement of experienced attachment or a prescription for its users.

Treat this Anxious 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 an Anxious-attached person.

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

Conflict

Frame it inside the relationship, not against it. Anxious-attached people hear critique as evidence of withdrawal. "We're good — and I want to flag X" opens the door that bare critique closes.

Feedback

Warm AND clear. Anxious attachment reads a clear note without warmth as rejection. Be explicit: "This isn't about us, it's about the work — and the work has this gap."

Decisions

Help them tolerate the gap between asking and answer. Anxious-attached people interpret silence as bad news. Give a timeline: "I'll come back Thursday — silence until then doesn't mean anything."

Brainstorming

Frequent affirmation that their contributions are heard. Anxious-attached people will over-monitor for signs they're being dismissed; explicit acknowledgment frees them up.

Explaining your preferences

§ V · If this is you

How to explain yourself outward.

The other direction. What Anxious-attached people sound like to other types — and how to bridge the gap when it matters.

How you come across

Too eager for reassurance. The need for confirmation can read as needing constant validation. People who don't externalize feelings may feel pressured by the regular check-ins.

Stating needs

"I'm reading silence as bad news right now — I know it's probably not, but if you can give me a quick read, it helps."

Boundary script

"I need a yes or no — the ambiguity is harder than either answer."

Recovery pattern

When you've over-pursued reassurance: "I was reading more into the silence than was there. Resetting."

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.

Secure attachment. Speak to me as a capable peer. Its first rule: Communication style.
Avoidant attachment. Respect my autonomy, space, and boundaries. Its first rule: Communication style.
Disorganized attachment. Keep your tone predictable, calm, and respectful. Its first rule: Communication style.

Not sure of your type? Take the free attachment-style test. It runs in your browser and links to the matching file. More on using Attachment with AI: How to give your AI a personality.

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/attachment/anxious.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/attachment/anxious.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.