## Definition **Plan mode** and **build mode** are the two operational modes of an agentic CLI distinguishing *reading the world* from *changing it*. ## Plan Mode Read-only. The agent can use Read, Grep, Glob, the LSP, and shell commands flagged as read-only. It **cannot** edit, write, or run mutating shell commands. Use when: - You don't yet know the shape of the change. - You want a proposal you can review before any code moves. - You're new to the codebase and the agent is faster at orienting you than you are. The agent finishes by emitting a structured plan you approve, reject, or amend. ## Build Mode The default — read, write, run, commit (if authorised). Use once a plan is in hand, or for tasks small enough that the plan is implicit. ## When to Flip Mid-Task Switch back to plan mode mid-build when: - The agent surfaces an unexpected branch ("I see this also affects X — do you want me to handle that?"). - A test you didn't expect to touch starts failing. - You feel the urge to write a 200-token prompt to "guide" the next step — that prompt *is* a plan; promote it. ## Common Mistake Flipping into build mode too early on cross-cutting work — getting a plausible-but-wrong implementation — then arguing with the agent turn after turn. A 90-second plan-mode pass eliminates this loop. ## Related - [[Agentic CLI]] - [[Specialized Agent]] - [[Sequential Pipeline]]