Stateful agentic engineering workflow for local coding agents
19 files for Codex, OpenCode and Claude Code: hard-eng AGENTS.md, he-build, he-learn, he-plan and 15 more — 894 tokens loaded in every session.
AGENTS.md C 894 tok .claude/settings.json A — .claude/settings.json A — .claude/settings.json A — .claude/settings.json A — .claude/settings.json A — .agents/skills/he-build/SKILL.md A 51 tok .agents/skills/he-learn/SKILL.md A 45 tok .agents/skills/he-plan/SKILL.md A 58 tok .agents/skills/he-ship/SKILL.md A 52 tok .agents/skills/he/SKILL.md A 27 tok .agents/skills/research/SKILL.md A 47 tok .agents/skills/security-review/SKILL.md A 58 tok .agents/skills/code-review/SKILL.md A 39 tok .agents/skills/codebase-design/SKILL.md A 45 tok .agents/skills/e2e/SKILL.md A 42 tok .agents/skills/product-walkthrough-video/SKILL.md A 44 tok .agents/skills/writing-great-skills/SKILL.md A 20 tok .agents/skills/marketing-video/SKILL.md A 50 tok These files are sgaabdu4/hard-eng's own configuration — they tell Codex, OpenCode and Claude Code 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.