self-extending sandboxed agentic harness. a loop, two tools and an llm
These files are av/mi's own configuration. They tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.
AGENTS.md A 2,105 tok CLAUDE.md A 3 tok .agents/skills/agent-integration-testing/SKILL.md A 20 tok .agents/skills/anneal/SKILL.md A 49 tok .agents/skills/bugbash/SKILL.md A 58 tok .agents/skills/bughunt/SKILL.md A 52 tok .agents/skills/discipline/SKILL.md B 58 tok .agents/skills/facts-discover/SKILL.md A 82 tok .agents/skills/facts-implement/SKILL.md A 48 tok .agents/skills/facts-refine/SKILL.md A 68 tok .agents/skills/facts/SKILL.md C 49 tok .agents/skills/ideate/SKILL.md A 89 tok .agents/skills/timeboxed-iterating/SKILL.md A 32 tok