Skip to content
Back to skills

Plan Review

ASecurity

Review implementation plan for completeness, simplicity, and risks

  • 48 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 2, 2026
ai-agentsgit

Works with

  • mcp

Security analysis

A100/100

Scanned September 2, 2026

npx -y skills add MarcusJellinghaus/mcp-workspace --skill plan_review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Plan Review?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Plan Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/marcusjellinghaus-plan-review/badge)](https://www.skillsdirectory.com/skills/marcusjellinghaus-plan-review)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
description: Review implementation plan for completeness, simplicity, and risks
allowed-tools:
  - mcp__mcp-workspace__git
  - mcp__mcp-workspace__read_file
  - mcp__mcp-workspace__list_directory
  - mcp__mcp-workspace__search_files
---

# Review Implementation Plan

**First, ensure we're up to date:**
Call `mcp__mcp-workspace__git` with command `"fetch"` and args `["origin"]`.
Use `mcp__mcp-workspace__git` with command `"status"` to check working directory state.

Confirm and display the current feature branch name.

---

**Then review the plan:**

Please review the project plan for a new feature in folder `pr_info/steps`.
Please revise the project plan with a balanced level of detail.
Please let me know if any complexity could be reduced.
Please let me know any questions / comments or suggestions you might have.

Please consider the already discussed and decided decisions (if any) under decisions.
We do not need to challenge them again unless absolutely necessary.

**Focus on:**
- Completeness of implementation steps
- Appropriate level of detail
- Opportunities for simplification (KISS principle)
- Test coverage strategy
- Step granularity — each step should produce exactly one commit. Flag steps with multiple independent parts (A, B, C) that should be split.
- Potential risks or blockers
- **Requirement changes** — flag new dependencies (`pyproject.toml`) that should be applied during planning, not deferred to implementation

For planning standards, see `.claude/knowledge_base/planning_principles.md`.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.