Skip to content
Back to skills

Ultraplan

ASecurity

Produce a detailed, reviewable implementation plan for a DockTerm change before building it.

  • 7 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 1, 2026
ai-agentsgitsecurity

Security analysis

A100/100

Scanned October 1, 2026

npx -y skills add munvard/dockterm --skill ultraplan --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ultraplan?

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

Security grade badge for Ultraplan
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/munvard-ultraplan/badge)](https://www.skillsdirectory.com/skills/munvard-ultraplan)

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: ultraplan
description: Produce a detailed, reviewable implementation plan for a DockTerm change before building it.
---

# Ultraplan

Turn an agreed design into a step-by-step plan that another contributor could
execute without context.

Cover:

- Scope and the exact files to create/modify (use real paths).
- The IPC contract changes: new channels in `src/shared/ipc.ts` (type + runtime
  allowlist), the zod-validated handler, and the service it calls.
- Data flow renderer ↔ main, and any store changes.
- Security: filesystem jail usage, `gitInvoke` for git, `secretMask` for any
  config display.
- Tests to add in `tests/unit` (pure logic: parsers, mappers, validators).
- The order to build in, and acceptance criteria.

Stop and get approval before implementing. Keep `npm run typecheck && npm test &&
npm run build` green at every step.

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…