Shape how your agents think

I built a skill package that gives each AI agent a distinct thinking style, and upgrades the council skill into a forum of truly independent thinkers. The result: agents that think differently on purpose - tailored to task - for sharper, well-rounded output.

First, I want to credit

@Curtis Hays

and

@Brooke Hays

for the inspiration. If you haven't watched their video in the post "If Your Specialized Agents Don't Think Differently. They Should." - please do. This is their work, I just wrote some files.

They touched on something I've been trying to crack since I started messing with agents a few months ago: how do I make an agent think in specialized ways? How can I get an agent to think from first-principles? How can an agent see things in ways that no one else would? How can an agent connect the dots that I am missing?

I tried assigning personalities, pointing agents at a knowledge base, etc, etc. Sometimes this worked - but often, they would fall back to whatever llm baseline was dictating their behavior.

Brooke's breakdown of cognitive functions, and Curtis' brilliant idea to assign them to his agents was the spark I needed.

I started by re-acquainting myself with the personality types, and building a COMPENDIUM: A reference guide to the 8 Jungian cognitive functions, the 16 MBTI types and their full stacks, and how each maps to an AI agent role. It was built from Carl Jung and Isabel Briggs-Myers' work. It's the single source of truth the other two skills read from — the "textbook" behind the system. The result: a shared, verified vocabulary for giving any agent or task a defined thinking style.

Then I got to work on figuring out how I could incorporate this into my ICM workspaces. This led to making the COGNASSIGN skill: A skill that assigns the right cognitive "Mind" to one agent or task. You answer a few job-first questions (what must it do, perceive, judge, and be best at), and it picks a lead function plus a balanced partner, then writes a small procedural block telling the agent how to think — not a personality label. If a job needs too many strengths it tells you to split it into two agents; if it's pure mechanical work it returns "N/A." The result: any agent gets a fit-for-task wiring in one drop-in block, the way the video's two agents thought differently from just four letters.

I'm also a fan of using the council skill when brainstorming or auditing. The multi-model council (Anthropic, OpenAI, Grok, etc) works great. But when confined to one provider with different model tiers, the results aren't always as impressive. But Curtis' post inspired me to ask "why not assign each council member its own cognitive function?" 5 distinct agents, with totally different thinking/perceiving styles. So I built an upgraded take on the council skill -the FORUM: A cognitive council that tackles a hard question from several thinking styles at once. A fixed panel (big-picture, first-principles, and unconventional thinkers) plus two stacks picked for the specific topic each give an independent take, anonymously peer-review each other, and an ENTJ "chair" synthesizes a final answer and flags where they disagreed. It works by running these as parallel agents through take → review → synthesis. The result: a stress-tested, well-rounded decision instead of one model's average-of-the-internet answer.

Try it out: https://github.com/julianargus01/agent-minds

Feedback is welcome.

10 comments