Janz

Rule-based labeling for AGENTS.md files. 558 files labeled against a 9-category taxonomy; numbers reported honestly, including the bad ones.

Joined on Sep 14, 2026 https://github.com/janzong/agent-charters

Janz

Oct 13

Audit your UI before you redesign it: baseline first, then compare

#ui #design #agents #opensource

3 min read

Want to connect with Janz?

Create an account to connect with Janz. You can also sign in below to proceed if you already have an account.

Create Account

Already have an account? Sign in

Janz

Oct 12

Four cognitive operations and a flywheel: what agents should actually do to knowledge

#ai #agents #knowledge #philosophy

4 min read

Janz

Oct 12

From shadow to gate: how we fixed agent citation fraud in one production batch

#ai #agents #governance #opensource

3 min read

Janz

Oct 11

I preregistered 30 real agent tasks. Three rules didn't survive contact.

#ai #agents #governance #opensource

3 min read

Janz

Sep 23

Your agent run passed. Can you prove it was allowed?

#ai #agents #governance #opensource

2 min read

Janz

Sep 22

We ran 2 vs 4 agents six times. Four agents cost 2.1 and did not improve success

#ai #agents #llm #opensource

3 min read

CLAUDE.md ties the format race

Janz

Sep 19

How common is AGENTS.md, really? I sampled GitHub: 6.2% of active repos, 1.0% of all repos

#ai #agents #github #opensource

6 min read

Janz

Sep 14

I looked at 558 AGENTS.md files: here's a 5-minute check for yours

#ai #agents #devtools #productivity

5 min read

Janz

Sep 14

I labeled 558 AGENTS.md files. Here's what they say — and what almost nobody writes down

#ai #agents #opensource #data

4 min read

DEV Community

Janz

Badges

2 Week Community Wellness Streak

1 Week Community Wellness Streak

Writing Debut

Audit your UI before you redesign it: baseline first, then compare

Want to connect with Janz?

Four cognitive operations and a flywheel: what agents should actually do to knowledge

From shadow to gate: how we fixed agent citation fraud in one production batch

I preregistered 30 real agent tasks. Three rules didn't survive contact.

Your agent run passed. Can you prove it was allowed?

We ran 2 vs 4 agents six times. Four agents cost 2.1 and did not improve success

How common is AGENTS.md, really? I sampled GitHub: 6.2% of active repos, 1.0% of all repos

I looked at 558 AGENTS.md files: here's a 5-minute check for yours

I labeled 558 AGENTS.md files. Here's what they say — and what almost nobody writes down