Working discipline for agentic coding sessions, distilled from Claude Code's official best-practices doc: close the loop with runnable verification (tests, /goal, Stop hooks, adversarial review subagents), separate explore/plan/code phases, keep CLAUDE.md lean, choose permissions/sandboxing deliberately, manage context aggressively (/clear, /compact, checkpoints), and scale with fan-out and agent teams. Use at the start of any non-trivial coding-agent session, when configuring an agent environment, or when a session shows drift, bloat, or unverified "done" claims.
