AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Plan Project

skill-martian56-claude-engineer-plan-project · by martian56

Use after the project brief is agreed, to produce a phased, multi-file implementation plan with a hard human sign-off gate, before any build work begins. Establishes the decision log and durable state files.

↗ Repository
— No reviews yet
0 installs
4 views
0.0% view→install

Install

$ agentstack add skill-martian56-claude-engineer-plan-project

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Plan Project? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Plan Project

Announce at start: "I'm using claude-engineer:plan-project to produce the phased plan."

Iron Law

NO BUILD WORK BEFORE THE USER SIGNS OFF ON THE PLAN. Violating the letter is violating the spirit.

Procedure (create a task per step)

  1. Decompose with superpowers:writing-plans - turn the agreed brief into bite-sized, testable tasks; map the file structure first; right-size tasks; bake in DRY/YAGNI/TDD.
  2. Impose the customer-experience-first phase order. Default phases:
  • Phase 0 - Conventions & scaffold (project-conventions, monorepo-and-tooling, docker-dev-environment).
  • Phase 1 - Design system (design-system: DESIGN.md is the source of truth).
  • Phase 2 - Frontend shells & components (frontend-development, on-token, WCAG AA).
  • Phase 3 - Backend APIs & data (backend-development).
  • Phase 4 - Integration & end-to-end flows.
  • Phase 5 - Quality, CI/CD, finish (testing-and-quality, ci-cd-pipeline).
  1. Write the plan as multiple files under docs/plan/ - 00-overview.md plus one file per phase (01-design-system.md, 02-frontend.md, …), each with goals, tasks, file targets, and the per-phase "definition of done" (the four quality gates).
  2. Record a decision log at docs/plan/decisions.md (every non-obvious choice + why).
  3. Initialize durable state via claude-engineer:project-memory (creates .claude-engineer/memory.md, progress.md, current-phase.txt).
  4. HARD SIGN-OFF GATE. Present the plan and explicitly ask the user to approve. Do not proceed to claude-engineer:execute-build until they do.

Quality bar baked into every phase's "done"

Tests + coverage · Playwright E2E with zero console errors · WCAG AA · strict types + lint clean. (See claude-engineer:testing-and-quality.)

Red flags - STOP

  • About to scaffold/build code while still "planning" → stop; finish the plan and get sign-off.
  • A phase has no concrete "definition of done" → add the four gates.
  • The plan lives in one giant file → split into docs/plan/* so it survives and stays scannable.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills