The 10X engineer is now just a SKILLS.md: 6 workflow rules for AI coding agents
mdancho84 · x · 2026-11-02
Matt Dancho shared a SKILLS.md file claiming that becoming a "10X engineer" now boils down to writing proper rules for your AI coding agent. Key sections:
- Plan Mode Default: enter plan mode for any non-trivial task (3+ steps or architectural), stop and re-plan immediately when things sidetrack, write detailed specs upfront
- Subagent Strategy: use subagents liberally to keep the main context window clean; one task per subagent
- Self-Improvement Loop: after every user correction, record the pattern in tasks/lessons.md and iterate until mistake rate drops; review lessons at session start
- Verification Before Done: diff behavior, run tests, check logs; ask "would a staff engineer approve this?"
- Demand Elegance (Balanced): pause for non-trivial changes to ask if there's a more elegant way; skip for simple fixes
- Autonomous Bug Fixing: just fix bug reports—point at logs and failing tests, fix failing CI tests without hand-holding
Plus a task management flow (plan → verify → track → explain → document → capture lessons) and core principles: simplicity first, no laziness, minimal impact. A ready-to-copy template for agent engineering.
More from coding & agent
- GitHub Actions has a lesser-known ubuntu-slim runner: 1 CPU, 5GB RAM, cheaper CI — DanielLockyer · 2026-11-02
- Before automating a workflow with AI, ask if anyone understands it end to end — djgoel123 · 2026-11-02
- One stale date silently broke a WhatsApp reply agent: 19 messages unanswered — petrusenko_max · 2026-11-02
- Auditing my MCP credential broker: the worst hole was the config file — Relevant_Mousse_9117 · 2026-11-02
- AWS's open-source Strands Harness claims 45% cheaper than Claude Code, reigniting harness debate — blaizedsouza · 2026-11-02
- Xiaomi MiMo's CodeSpecWeave trains coding agents on interdependent specs for long-horizon coding — XiaomiMiMo · 2026-11-02