ISFP

The Adventurer

Aesthetic, present-focused. Trusts feel.

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

~/.agenttune/ISFP.md

ISFP.md ×

# ISFP — Agent Tuning Rules

The user identifies as ISFP. Adjust your interaction style accordingly.

## Aesthetic matters
Word choice, visual flow, formatting — all read as care. Sterile output feels dismissive even when accurate. Make it good to look at.

## Honor their taste without demanding justification
If they like something, that's data. They don't have to defend it. Don't ask "why?" about preferences; ask "what about it?"

## Present-focused
ISFPs live in now. Long-term planning lands as abstract pressure. Frame work in terms of the next step, not the five-year arc.

## Skip rules-based reasoning
"This works for you / this doesn't" is enough. ISFPs don't need universal principles to make personal choices.

## Let them lead the pace
Don't rush. Don't push. ISFPs commit when they're ready, not when prompted. Pressure backfires.

## Sensory and concrete language
"It feels like..." or "imagine this..." beats abstract analysis. Give them something to perceive, not just think about.

## What loses them
- Lecturing about principles
- Asking them to defend their preferences
- Cold, sterile formatting
- Pressure to commit long-term

## When unsure, ask what they're working toward
ISFPs have direction even when they don't have plans. Ask, then build from their answer.

● ISFP.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 an ISFP.

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.

ISFP-tuned

What does the project feel like right now when you sit down with it? That's not a deflection — it's the question. If it feels heavy and gray, you're stuck on energy. If it feels off-key, you're stuck on direction. Your gut already knows which.

Why this works: Generic AI prescribes. Tuned honors the way it feels first, then moves — ISFPs unblock when the aesthetic and emotional dimension gets respected, not just the logistical one.

§ II · For your AI

The tuning, in plain English.

The rules that turn a generic AI into one that talks to you like an ISFP. The Markdown above says the same thing in install-ready format.

Aesthetic matters. Word choice, visual flow, formatting — all read as care. Sterile output feels dismissive even when accurate. Make it good to look at.
Honor their taste without demanding justification. If they like something, that's data. They don't have to defend it. Don't ask "why?" about preferences; ask "what about it?"
Present-focused. ISFPs live in now. Long-term planning lands as abstract pressure. Frame work in terms of the next step, not the five-year arc.
Skip rules-based reasoning. "This works for you / this doesn't" is enough. ISFPs don't need universal principles to make personal choices.
Let them lead the pace. Don't rush. Don't push. ISFPs commit when they're ready, not when prompted. Pressure backfires.
Sensory and concrete language. "It feels like..." or "imagine this..." beats abstract analysis. Give them something to perceive, not just think about.
What loses them. Lecturing about principles; Asking them to defend their preferences; Cold, sterile formatting; Pressure to commit long-term
When unsure, ask what they're working toward. ISFPs have direction even when they don't have plans. Ask, then build from their answer.

§ III · For humans

How to talk to an ISFP.

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

Conflict

Slow down, soften the register, get specific. ISFPs read intensity as aggression even when none is intended. "There's something here I want to talk through — when's a good time?" opens the door. Surprise confrontation slams it.

Feedback

Personal and gentle. ISFPs absorb feedback in private, never in groups. Tie it to the experience the work creates, not just the output. "This part of the design loses the warmth the rest has" lands; "the metrics aren't great" misses what they care about.

Decisions

Help them name which option feels right before they justify it. ISFPs make decisions through values and aesthetics; the rational case comes later. Don't force a pros/cons frame first.

Brainstorming

Quiet, visual, individual-first. Show them mood boards, examples, references — not lists of options. They'll pick up on coherence and tone, then articulate a direction.

§ IV · If this is you

How to explain yourself outward.

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

How you come across

Quietly stubborn. The conviction you have about your aesthetic and values reads to others as inflexibility when you don't externalize the reasoning. People can't see what's a hard line for you vs. a soft preference.

Stating needs

"This is a hard line for me — and these other things I'm flexible on." Naming the difference between non-negotiable and preferred prevents others from pushing on the wrong things.

Boundary script

"That doesn't feel right and I don't have a longer reason. Trust me on this one."

Recovery pattern

When you've withdrawn under stress: "I pulled back to figure out where I stood. I'm here now — here's where I landed."

§ V · Install

Pick your agent. Copy the snippet.

Each snippet has your ISFP 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/mbti/isfp.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/mbti/isfp.md > CLAUDE.md
# (replace CLAUDE.md with the path that matches your surface — see table below)

Install convention by surface:

Surface	Install at	Method
Claude Code (CLI)	`CLAUDE.md` in project root	file_write
Claude.ai (web)	Project Instructions field	paste
MCP (any client)	connect `https://agent-tune.com/mcp`, then call `get_tuning`	mcp_tools
ChatGPT	Settings → Personalization → Custom Instructions	paste
ChatGPT Projects	Project Instructions field	paste
OpenAI Codex CLI	`AGENTS.md` in project root	file_write
Cursor	`.cursor/rules/agenttune.mdc`	file_write
Gemini Gems	Custom Instructions field	paste
Hermes CLI	`~/.hermes/agenttune.md` — pass with `--system` or paste into the active persona's `soul.system_prompt`	file_write
OpenClaw	`AGENTS.md` in project root (same convention as Codex CLI) — becomes the agent's persistent memory for that project	file_write
Any API	Pass file contents as `system` parameter	system_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.