AgentStack
SKILL verified MIT Self-run

Planning Engine

skill-yipxiyi-openarc-planning-engine · by Yipxiyi

Use when producing a lightweight implementation plan before coding, including scope, affected systems, migration, rollback, tests, reuse, and architecture impact.

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

Install

$ agentstack add skill-yipxiyi-openarc-planning-engine

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

About

Planning Engine

Use this skill before implementation when a change has meaningful scope, risk, or cross-file impact.

Goal

Create a short, executable plan that helps agents implement the right change in the right order.

If the goal, non-goals, constraints, acceptance criteria, or target docs are not stable, run clarification-gate before writing the plan.

Plan Requirements

A plan should answer:

  • What changes
  • Why it changes
  • Affected systems
  • Existing code or docs to reuse
  • Migration requirements
  • Rollback strategy
  • Testing strategy
  • Architecture impact
  • Risks and open questions
  • Version impact and whether user confirmation is needed

Output

Use templates/PLAN.template.md as the default shape. Save plans under docs/plans/ when the repository keeps persistent plans. Otherwise, keep the plan in the conversation and execute it.

Rules

  • Keep plans lightweight.
  • Prefer the shortest viable path.
  • Do not turn routine changes into ceremony.
  • Do not proceed to implementation if the plan exposes unresolved blockers that would make the work risky or incoherent.
  • Use Clarification Gate output as the preferred input when the request started broad, ambiguous, or cross-cutting.
  • Use version-governance when the plan implies patch, minor, or major release impact.

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.