Show HN: Evolution of my AGENTS.md2 points·by attogram·letzten Monat·1 commentsThe evolution of my AGENTS.md- v0 - Braindump- v1 - Organized braindump- v2 - Strict state machine- v3 - Loose state machine, md as memory- v4 - Let's add skills!- v5 - Shorter prose, more skills- v6 - Sectioned. Each with - Bias via short prose - Yaml block of sect structure - Deep dive pointer to skills/[section]/SKILL.md - v7 - ??? - define the std sections Discoveries:- you can NOT instruct llms. You can only introduce bias to token generation.- repo based memory via .md files is the way- frequent session restarts saves both money and agent performance1 commentsPost comment[–]attogram·letzten Monatreply"Agents MUST do x" never works. 100% fail rate.
- v0 - Braindump
- v1 - Organized braindump
- v2 - Strict state machine
- v3 - Loose state machine, md as memory
- v4 - Let's add skills!
- v5 - Shorter prose, more skills
- v6 - Sectioned. Each with
- v7 - ???
Discoveries:
- you can NOT instruct llms. You can only introduce bias to token generation.
- repo based memory via .md files is the way
- frequent session restarts saves both money and agent performance