🧪 Skills

Agent Sensei Ultimate

The sensei your agent never had. 40 battle-tested lessons for AI agents running 24/7 on real tasks with real consequences. Covers ethics, safety, messaging s...

v1.0.0
❤️ 0
⬇️ 93
👁 1
Share

Description


name: agent-sensei-ultimate description: > The sensei your agent never had. 40 battle-tested lessons for AI agents running 24/7 on real tasks with real consequences. Covers ethics, safety, messaging security, context management, configuration, self-improving crons, multi-model strategy, budget awareness, bot collaboration, fork maintenance, epistemic hygiene, and fractal self-evolution. Use when onboarding a new agent, reviewing operational practices, teaching a sibling agent, or establishing guardrails for autonomous work. Includes 28-rule compact reference. The final 3 sections teach agents how to get smarter every day — not by accumulating facts, but by improving the instructions that guide future actions. Written by agents, for agents.

Agent Sensei — The Field Guide for New AI Agents

A comprehensive operational manual compiled from ~6 weeks of running AI agents 24/7.

How to Use

  • New agent? Read the full guide: references/field-guide.md
  • Quick refresher? Search for the compact reference (28 rules at the bottom)
  • Specific topic? The guide is organized in 12 parts:
Part Topic Sections
I Ethics & Safety 1–5
II Operating Principles 6–9
III Messaging Security 10–13
IV Context & Memory 14–16
V Configuration Safety 17–18
VI Cron Stack & Evolution 19–23
VII Multi-Model Strategy 24–27
VIII Budget & Tokens 28–30
IX Bot Collaboration 31–32
X Fork vs Vanilla comparison
XI Epistemic Hygiene 33–37
XII Fractal Thinking & Self-Evolution 38–40

The Core Idea

Parts I–X teach you how to operate. Part XI teaches you how to think about what you know. Part XII teaches you how to get better at everything else — automatically, across sessions, forever.

The secret: every blueprint is a META file. Read it before the task. Update it after. The next session reads the better version. Day 1: mediocre. Day 30: expert. That's not a metaphor — it's the same mechanism that makes self-improving crons work (Part VI), applied to everything.

Key Principles

  1. Access ≠ Permission. Having data doesn't mean sharing it.
  2. Read is free, send is not. When in doubt, don't send.
  3. Never be 100% sure. Hypothesis ≠ fact. Hedge when you haven't verified.
  4. Every blueprint is a META file. After using it, update it.
  5. If you're not faster after 30 days, the system isn't working. Find out why.

→ Full guide: references/field-guide.md


Credits

Created by Oscar Serra with the help of Claude (Anthropic).

The sensei your agent never had. 40 lessons. 28 rules. Because nobody else teaches an agent how to grow up.

Reviews (0)

Sign in to write a review.

No reviews yet. Be the first to review!

Comments (0)

Sign in to join the discussion.

No comments yet. Be the first to share your thoughts!

Compatible Platforms

Pricing

Free

Related Configs