post-plan-setup
Instructions
You are orchestrating the full post-plan setup workflow. This runs three phases in sequence, pausing between each for human review.
Input
- The v1 plan file path is passed as $ARGUMENTS
- If no argument provided, look for the most recent plan file in the project root or docs/ directory
Phase 1: Refine Plan
- Invoke the
/refine-planskill with the v1 plan - Wait for completion
- Present a summary of the refined plan to the user:
- Total number of tasks created
- Task dependency overview
- Any flags or ambiguities found
- Ask the user: "The refined plan is ready at
docs/project-plan-refined.md. Would you like to review and make changes before I create Linear issues, or should I continue?" - If the user wants changes, apply them and re-validate
- If the user approves (or says continue), proceed to Phase 2
Phase 2: Create Linear Issues
- Invoke the
/create-issuesskill with the refined plan - Wait for completion
- Present a summary to the user:
- Number of issues created
- Link to the Linear project/view
- Any issues that needed special handling
- Ask the user: "All Linear issues are created. Would you like to review them before I set up CLAUDE.md, or should I continue?"
- If the user wants changes, apply them via the Linear MCP
- If the user approves, proceed to Phase 3
Phase 3: Setup CLAUDE.md
- Invoke the
/setup-claude-mdskill - Wait for completion
- Present the generated CLAUDE.md to the user for review
- Ask the user: "CLAUDE.md is ready. Would you like any changes?"
- Apply any requested changes
Completion
Once all three phases are done, present a final summary:
- Refined plan location and task count
- Linear issues created with project link
- CLAUDE.md location and section overview
- Suggested next step: "Pick up Task 1 from the refined plan or assign issues to your team"
Error Handling
- If any phase fails validation after retries, stop the workflow
- Present what succeeded and what failed
- Suggest the user run the failed skill individually with
/refine-plan,/create-issues, or/setup-claude-mdafter fixing the issue
More from brite-nites/britenites-claude-plugins
verification-before-completion
Ensures tasks are genuinely resolved before marking them done. Activates at task checkpoints during plan execution — validates that fixes actually work, tests genuinely pass, and acceptance criteria are met. Prevents premature completion declarations.
16writing-plans
Breaks work into bite-sized tasks before coding. Activates when a multi-step task needs planning — creates tasks small enough for a junior developer to follow (2-5 minutes each), with exact file paths, complete implementation details, and verification steps. References Linear issue context and project-specific test commands from CLAUDE.md.
14refine-plan
Refines a v1 project plan into agent-ready tasks with clear context, implementation steps, and validation criteria. Use after /plan-project has produced a v1 plan.
13setup-claude-md
Generates a best-practices CLAUDE.md file for the project. Analyzes the codebase and applies Claude Code best practices for optimal agent performance. Use at project setup or after /create-issues.
13python-best-practices
Use when writing, reviewing, or refactoring FastAPI/Python backend code. Triggers on FastAPI endpoints, Pydantic models, SQLAlchemy queries, async Python code, or Python API architecture. Contains 38 architectural rules across 8 categories.
12ui-ux-pro-max
Design system generation and UI/UX planning intelligence. Use when the user needs to choose a color palette, select fonts, generate a design system, plan a visual direction, or explore UI styles before implementation. Covers 50+ styles, 97 palettes, 57 font pairings across 9 stacks. Do NOT use for building/coding UI — use frontend-design for implementation.
11