Agent Instructions
One file at the root. Everything else follows from it.
The Foundation topic gave the repo its structure. Agent Instructions is what makes that structure legible to the agent. Without it, the agent improvises from general training data. With it, the agent reads this codebase.
The chapters in this topic cover the mechanics: what goes in AGENTS.md, how to build the instruction hub it points into, how to write instructions that change agent behavior, and how to keep instruction load within the context window. Hooks are part of the hub too, but they are optional and maturity-dependent. Leave that directory empty until the rest is stable.
Chapters
- AGENTS.md: The Entry Point: the TOC pattern, what goes in it, vendor pointers, and why it has to stay short
- Agent Instruction Hub:
.agents/instructions/,.agents/skills/,.agents/hooks/, one folder for all agents - Instructions That Work: specific instructions, negative constraints, architecture boundaries, and how to test whether they work
- Skills, Commands, and Hooks: when to choose each type, how to write skills that run reliably, and the instruction/skill/hook triangle
- Context Window Management: why context fills, short sessions, selective loading, subagents, and the INDEX as context economy