Skip to content

Planning

Cosine can investigate before it acts. When a task is large, ambiguous, or risky, the agent may suggest entering Plan mode so it can produce a structured plan before making any changes. If you know you want a plan before starting a task, you can request one by operating the agent in Plan mode.

Cosine can plan when:

  • You explicitly switch to Plan mode before sending a prompt
  • You ask Cosine to plan before implementing
  • The task spans many files or modules
  • The request is ambiguous and needs clarification
  • The agent detects that planning would reduce risk or rework

If Cosine proactively suggests Plan mode, it asks for your confirmation before entering it. If you explicitly ask Cosine to plan, it can start planning directly.

  1. Explore — The agent reads relevant files and asks clarifying questions
  2. Draft — The agent writes a step-by-step implementation plan
  3. Present — The plan is shown to you for review and approval
  4. Proceed — You choose how to continue: approve and execute, revise, or reject

After Cosine has finished creating a plan in Plan mode, it will ask you how you want to proceed before implementation starts. These options control whether Cosine implements automatically, asks for manual approval, revises the plan, or exits Plan mode.

OptionWhat it does
Yes, clear context and auto-accept editsClears the conversation history, keeps the plan, and switches to Auto mode for implementation. This can free up space in the context and works best if the plan is self-contained
Yes, auto-accept editsKeeps the full conversation and switches to Auto mode
Yes, manually approve editsKeeps the conversation and switches to Manual mode so you approve each change
Yes, accept and enable Swarm modeHands the plan to a swarm of subagents for parallel execution
Type feedbackProvide feedback on the plan so the agent can revise it
Reject, and exit plan modeDiscards the plan and returns to the previous mode

Planning is useful when:

  • The task is large or ambiguous and you want to align on approach before writing code
  • You want a written record of the intended changes before they happen
  • You’re exploring trade-offs between different implementation strategies
  • You want to review scope before committing time and tokens