From plan
Provides guidelines for high-quality implementation plans: structure with context/changes/verification/risks, scope matching requests, pre-reads, and rejection analysis.
How this skill is triggered — by the user, by Claude, or both
Slash command
/plan:guidelinesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
@references/guidelines.md
@references/guidelines.md
Before proposing any changes:
A good plan includes:
Plans should match the request exactly:
Common reasons for plan rejection:
npx claudepluginhub bendrucker/claude --plugin planEnforces a planning gate before code changes: investigate context, surface blockers, produce a step-by-step plan, and implement only after explicit approval.
Replicates Claude Code plan mode in read-only fashion: explores codebase, designs changes, gets user approval, then writes plan to .claude/plans/<slug>.md without executing. Triggers on 'plan only' phrases.
Guides writing or updating detailed plans for Claude Code sessions, assessing component readiness, filling knowledge gaps, defining testing strategies, and verifying hypotheses.