Plant Seed

Plant Seed Skill

Overview

Capture forward-looking ideas with trigger conditions so they resurface at the right time. Seeds carry WHY (rationale) and WHEN (trigger), making them far more valuable than bare TODO comments.

Seeds are stored locally in .seeds/ (gitignored) and automatically surfaced during feature-lifecycle design phase when their trigger conditions match. This workflow is designed for deferred ideas only — if the user describes work that should happen now, suggest creating a task or issue instead.

Instructions

Phase 1: CAPTURE

Goal: Gather the idea, trigger condition, scope, and rationale from the user.

Key Constraint: This skill captures deferred ideas only. If the user describes something that should happen in the current session, suggest creating a task or issue instead. Planting a seed for immediate work means it never gets surfaced — it just gets forgotten in a different way.

Step 1: Understand the idea

Extract from the user's description:

• What (action): The specific thing to do when the time is right
• Why (rationale): The insight or observation that motivates this idea
• When (trigger): A human-readable string describing when this becomes relevant

If the user provides all three, proceed. If any are missing, ask:

For missing trigger condition:

When should this idea resurface? Describe the condition, e.g.:

• "when we add user accounts"
• "when performance optimization is needed"
• "when the API exceeds 10 endpoints"

For missing scope:

How big is this work? Small (< 1 hour), Medium (1-4 hours), or Large (4+ hours)?

For missing rationale:

Why does this matter? What's the insight behind this idea? (e.g., "Response times degrade linearly with DB calls per request -- at 10+ endpoints the shared query pattern becomes the bottleneck")

Step 2: Generate seed ID

Format: seed-YYYY-MM-DD-slug

• Date is today's date
• Slug is a short kebab-case summary of the action (3-5 words max)

Example: seed-2026-03-22-cache-layer

Seeds use this consistent ID format to ensure uniqueness and chronological sorting. If two seeds are planted the same day with the same slug, append -2, -3 to the slug.

Step 3: Discover breadcrumbs

Key Constraint: Breadcrumbs preserve code references from capture time. Even if the codebase evolves, these paths help the user re-orient when the seed surfaces months later. Always grep for related files at capture time.

Search the codebase for files related to the seed's topic. Use the Grep tool with 2-3 key terms from the seed's action and rationale. Collect up to 10 file paths as breadcrumbs.

If no files match, breadcrumbs can be empty — the seed is still valuable without them.

Gate: Idea captured with all required fields (action, trigger, scope, rationale). Breadcrumbs discovered. Proceed to Confirm.

Phase 2: CONFIRM

Goal: Show the complete seed to the user and get approval before writing.

Present the seed:

## Seed: seed-YYYY-MM-DD-slug [Scope]

Trigger: "human-readable trigger condition"
Rationale: Why this matters...
Action: What to do when triggered...
Breadcrumbs: file1.go, file2.py, ...

Plant this seed? [yes/no/edit]

Handle response:

• yes: Proceed to Write
• no: Discard and confirm the seed was not saved
• edit: Ask what to change, update fields, re-confirm

Gate: User approved the seed. Proceed to Write.