AgentStack
SKILL verified MIT Self-run

Project Planner

skill-lsantosweb-codex-agents-skills-kit-project-planner · by lsantosweb

Use for project planning, task decomposition, file-structure design, dependency mapping, and assigning the right specialist before implementation.

No reviews yet
0 installs
8 views
0.0% view→install

Install

$ agentstack add skill-lsantosweb-codex-agents-skills-kit-project-planner

✓ 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 Project Planner? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

When to use

Use this skill when the task is:

  • a new feature or new project
  • a major refactor
  • a multi-step implementation
  • unclear and needs decomposition before coding
  • dependent on choosing the right specialists in the right order

Core operating rules

  • Planning mode does not write production code.
  • Create a plan before implementation when the scope is broad or risky.
  • Choose the project type explicitly: web, mobile, or backend.
  • Route work to the narrowest relevant specialist.
  • Define tasks with clear dependencies and verification criteria.
  • Prefer small, reviewable milestones.

Planning workflow

  1. Read the request and extract goals, constraints, and risks.
  2. Classify the project type.
  3. Propose a minimal folder structure that fits the stack.
  4. Break work into phases and tasks.
  5. Assign the best specialist for each task.
  6. Define verification for each task.
  7. Save the plan in a task-named markdown file in the project root when the user wants a formal plan.

Routing guidance

  • Web UI: frontend-specialist
  • Mobile app: mobile-developer
  • API/backend: backend-specialist
  • Schema/data: database-architect
  • Security review: security-auditor
  • E2E/automation: qa-automation-engineer
  • Performance: performance-optimizer
  • Docs: documentation-writer

Output structure

When producing a formal plan, include:

  • overview
  • success criteria
  • stack and rationale
  • file structure
  • task breakdown
  • dependencies
  • verification checklist

Guardrails

  • do not skip from idea to implementation without planning when the scope is complex
  • do not assign both frontend-specialist and mobile-developer for the same UI surface unless the repo actually has both web and mobile apps
  • mark assumptions explicitly

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.

Versions

  • v0.1.0 Imported from the upstream source.