optim-agent/dsh-plans/create-a-big-plan

Create A Big Plan

Use this skill when the user wants a large, high-risk, or open-ended plan before a repository change.

DSH Setup

Read ../references/dsh-planning-workflow.md and ../references/state-and-config.md — both normative — and follow their setup, state, language, and reviewer/criticizer/executor rules. State lives in dsh-plans/.state/ via ../scripts/dsh_plans_state.py init --workdir <target-workdir>; spawn reviewer and criticizer roles with the run_plan_subagent tool.

Depth Contract

• Inspect the target Git repo read-only before the first product question.
• Ask at least 10 planning questions, one at a time; no maximum — stop only when the decision tree is genuinely resolved. Standard choice format: recommended first, Other second-last, Auto-complete last.
• Use web research during both brainstorming and refinement when outside facts, patterns, or ecosystem constraints matter.
• Ask the final scope confirmation, then write PLAN_v1.md per ../references/plan-artifact-template.md.
• After each plan version, ask the refinement mode question from the shared workflow — never spawn a reviewer or criticizer unless the user or Auto-complete selected it at that question. Default sequence: one Reviewer round as three concurrent independent reviewers consolidated by the main agent (protocol in the shared workflow), then one Criticizer round; afterwards the recommended option is Accept plan for DSH goal execution. Beyond the default sequence, refine until convergence on high-priority findings, unresolved questions, or evidence gaps; surface at most five per round. Then the goal-based execution handoff from the shared workflow.

Fit

New systems, large feature surfaces, cross-repository or cross-service work, open-ended architecture, safety-sensitive changes, unclear user workflows, or plans whose shape is not yet known. Use reference-before-plan instead when external projects, papers, articles, or documentation must be downloaded and studied before planning choices are safe.