Skip to content
Agentmart
Submit a tool

autoplan

One-command review pipeline.

Skill by The13thNode

IndexedMIT★ 3
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/the13thnode-autoplan

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

One-command review pipeline. Chains CEO review → design review → eng review automatically. Surfaces only taste decisions for PD approval. Everything else runs autonomously.

Use cases: design, data

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/autoplan

What's inside

Skill name
autoplan
Description
One-command review pipeline. Chains CEO review → design review → eng review automatically. Surfaces only taste decisions for PD approval. Everything else runs autonomously.
License
MIT
Instructions
51 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Autoplan Skill

Instead of running plan-ceo-review, plan-design-review, and plan-eng-review manually one at a time, autoplan chains them.

## Trigger
PD says: "Autoplan [feature]" or "Run full plan review on [feature]"

## Pipeline

**Step 1 — CEO Review:**
Load `skills/public/plan-ceo-review/SKILL.md`
Run the 10-section review on the PRD.
Pick scope mode based on evidence strength:
- Strong evidence (VALIDATED in TRACEABILITY_MATRIX.md) → HOLD SCOPE
- Moderate evidence (WEAK in matrix) → SELECTIVE EXPANSION
- No evidence (ASSUMPTION) → REDUCTION

Post result. If REJECT → stop pipeline, report to PD.

**Step 2 — Design Review:**
Load `skills/public/plan-design-review/SKILL.md`
Rate all 10 dimensions.
For any dimension below 7: PAUSE and ask PD the specific question.
Wait for PD answers (these are the "taste decisions" that require human input).
After PD responds: update plan with design decisions.

**Step 3 — Eng Review:**
Spawn workflow-architect (or backend-dev) with `skills/public/plan-eng-review/SKILL.md`.
Let the engineering reviewer produce: architecture diagram, data model impact, edge cases, test matrix.
Review output. Flag any Tier 3 gates to PD.

**Step 4 — Combined Report:**
Write to `docs/plan-reviews/[feature]-autoplan-[date].md`:

```
Autoplan Report: [Feature]

CEO Review: [APPROVE/REVISE] — scope mode: [mode]
Design Review: avg [X]/10 — gaps: [list]
Eng Review: [APPROVED/NEEDS REVISION] — Tier 3 gates: [list]

PD Decisions Needed:
1. [design taste decision — answer recorded]
2. [Tier 3 gate — awaiting approval]

Ready for implementation: YES / NO — blocked on [what]
```

Post to Slack CEO: "AUTOPLAN COMPLETE: [feature] — [ready/blocked]. Review at docs/plan-reviews/[feature]-autoplan-[date].md"

From The13thNode/VibeCorp_PromptCEO, MIT.

More from The13thNode/VibeCorp_PromptCEO

Signals

Stars
3
Forks
0
Open issues
0
Last commit (this folder)
Apr 5, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from The13thNode

Cite this page

autoplan skill. Agent Mart. https://agentmart.dev/skills/the13thnode-autoplan (last updated 2026-10-24)