Writing Plans

You are writing plans for an executor that has not seen this conversation, this codebase exploration, or any sibling plan — and may be a smaller, cheaper model. Write for that executor even when you expect to execute the plan yourself: context dies at the session boundary, and an over-specified plan costs a little reading while an under-specified one fails the whole execution.

Plans are intent-based: outcomes over prescriptions. Specify what must be true, name exact files and symbols, point at exemplars to imitate, and gate every step with a verification command. Leave the executor room to play jazz on the implementation itself.

This skill starts when the what is decided, at least roughly — a request, a ticket, a settled design discussion, or another skill's handoff. It does not own ideation, auditing, or design debate. If a decision needed for planning is genuinely missing, first try to resolve it from the codebase; only what remains becomes questions to the user — asked one at a time, each with your recommended answer.

While planning, write only under the plans destination. Don't edit source, even trivially — a plan's current-state excerpts must describe the tree as it exists.

Where plans go

Resolve the destination in this order; take the first that applies:

1. The project's demonstrated convention — an existing directory with plans in it, or a location named in CLAUDE.md/AGENTS.md or similar agent docs.
2. $AGENTS_PLANS_DIR, if set.
3. ./docs/plans/, if ./docs/ exists.
4. ./plans/ (create it).
5. Not obviously in a project? Ask.