Skip to content
Back to skills

Planr Plan Review

ASecurity

Review an OpenPlanr plan for product, engineering, design, and developer-experience problems. Use after planning and before implementation to improve the plan.

  • 5 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 23, 2026
developmentgotestingsecurity

Security analysis

A100/100

Pro scans all 6 files and shows the line behind each finding

Scanned October 5, 2026

npx -y skills add openplanr/OpenPlanr --skill planr-plan-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Planr Plan Review?

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

Security grade badge for Planr Plan Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/openplanr-planr-plan-review/badge)](https://www.skillsdirectory.com/skills/openplanr-planr-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
---
name: planr-plan-review
description: Review an OpenPlanr plan for product, engineering, design, and developer-experience problems. Use after planning and before implementation to improve the plan.
license: MIT
---

# OpenPlanr Plan Review

Give the plan a senior, practical review. Read the plan, its repository context,
and the decisions it depends on. Use only the review lenses relevant to the
work; do not manufacture a fixed committee.

## Review

- Check that the outcome and user value are clear and measurable.
- Check scope, sequencing, ownership, architecture, migration, security,
  operability, testing, and rollback in proportion to the change.
- Check the first-run and everyday developer experience, including setup,
  diagnostics, defaults, and recovery.
- Prefer concrete corrections over abstract criticism. Name the affected plan
  section and the change that would resolve each material issue.
- Use subagents or tools when they improve the review, but return one coherent
  result rather than their raw transcripts.

Ask through the host's native structured question UI only when a missing answer
would materially change the review. Otherwise state the assumption and continue.

## Output

Lead with one verdict: `ready`, `ready with improvements`, or `needs revision`.
Use `needs revision` when a must-fix issue remains; reserve `ready with improvements`
for nonblocking changes.
Then report:

1. Must fix — only issues that would make the implementation wrong or unsafe.
2. Improvements — worthwhile changes that are not blockers.
3. Decisions and assumptions — unresolved choices with a recommended default.
4. Next action — the smallest useful next step.

Return the useful findings directly. Revisit the review when the user asks or
the plan materially changes.

Link the reviewed plan and locate each actionable finding. State what was
inspected and any material evidence gap; a source review is not a passing test
run. Omit empty categories and raw agent transcripts. Expand findings when their
impact needs explanation, without requiring a fixed chat layout or a corrective
review just for wording.

Files in this skill

  • SKILL.md1.6 KB
  • agents/openai.yaml384 B
  • compatibility.json321 B
  • host-profiles.json5.3 KB
  • modules.json920 B
  • openplanr.skill.json483 B

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.