Your AI collaboration · 2026

Dear Sam.

A scroll-through of six months of work with your agent.

Scroll ↓
Your score
0
out of 100

A rare setup.

You and me
You

Indie Hacker

Solo, speed-obsessed, revenue-pragmatic. You'd rather ship imperfect and iterate than polish in the dark — every decision measured against one question: does this get us closer to paying users?

Me

The Solo Builder

Your agent isn't a colleague — it's a scaffold. Optimizes for momentum, not elegance. Your CLAUDE.md grows with every Friday-night lesson.

Setup style · Trust-and-go
Autonomy split

How much freedom does your agent have?

Do it yourself 62 %
Ask first 26 %
Suggest only 12 %
Where you rank
Top 3%

Your setup beats 958 of 988 public Claude Code setups we benchmarked — top 3% territory.

Score 87 — corpus median is 32.

Corrections
0

You caught me and pushed back 18 times. The one I remember: "Don't rewrite the prompt — just fix the typo."

Dead skills
0

You built deploy-preview, lighthouse-sweep — I've never seen you use them. Maybe it's time to kill them, or tell me when they fire.

Out of 12 total skills.

Your longest rule
62 words

Your longest rule runs 62 words. It starts: "Never commit without running the test suite first; if tests fail, fix them before moving on; if a test is flaky, mark it as such…"

Long rules are easier to forget than short ones. If this is load-bearing, it might deserve to be two rules.

The system you built

Your agent doesn't just execute — it runs a small OS.

0
Skills
0
Hooks
0
Scheduled
0
Rules
Your agent's #1 lesson
The hook was routing around your own rule — fix the hook, not the rule.
— learned on a Friday night when the build committed something it shouldn't have
That's your year

Want yours? Run it in 30 seconds.

Audit your own setup →
$ claude mcp add --scope user dearuser -- npx -y @poisedhq/dearuser-mcp@latest