gsd-plan

Plan a phase — optional discussion → research → plan → verify

9 stars

bymlucascosta

View on GitHub Installation ↓

Best use case

gsd-plan is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Plan a phase — optional discussion → research → plan → verify

Teams using gsd-plan should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/gsd-plan/SKILL.md --create-dirs "https://raw.githubusercontent.com/mlucascosta/ia_boilerplate/main/.agents/runtimes/codex/skills/gsd-plan/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/gsd-plan/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How gsd-plan Compares

Feature / Agent	gsd-plan	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Plan a phase — optional discussion → research → plan → verify

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

<codex_skill_adapter>
## A. Skill Invocation
- Invoked by mentioning `$gsd-SLUG`.
- Treat all user text after `$gsd-SLUG` as `{{GSD_ARGS}}`.

## B. AskUserQuestion → request_user_input Mapping
- `header` → `header`, `question` → `question`
- Execute mode fallback: plain-text numbered list, pick reasonable default

## C. Task() → spawn_agent Mapping
- `Task(subagent_type="X", prompt="Y")` → `spawn_agent(agent_type="X", message="Y")`
- `Task(model="...")` → omit
- Parallel: spawn → collect IDs → `wait(ids)` → `close_agent(id)`
</codex_skill_adapter>

<objective>
Create an executable PLAN.md for a roadmap phase.

Default flow: Research (if needed) → Plan → Verify → Done

Flags:
- `--discuss` — Clarify assumptions before planning
- `--ui` — Generate UI design contract before planning
- `--auto` — Skip questions, use recommended defaults
- `--skip-research` — Go straight to planning
- `--gaps` — Gap closure mode from VERIFICATION.md
- `--prd <file>` — Parse PRD into CONTEXT.md
- `add-phase "desc"` — Append future phase to roadmap
- `insert-phase N "desc"` — Insert future phase after N
- `remove-phase N` — Remove future phase safely

After: run gsd-run <phase> to execute.
</objective>

<context>
Phase: {{GSD_ARGS}} (auto-detects next unplanned if omitted)
</context>

<process>
Route by intent:
- `add-phase` → add-phase workflow
- `insert-phase` → insert-phase workflow
- `remove-phase` → remove-phase workflow
- `--ui` → ui-phase workflow
- `--gaps` → plan-milestone-gaps workflow
- `--discuss` → discuss-phase workflow first, then plan-phase
- otherwise → execute plan-phase workflow end-to-end
</process>

<execution_context>
@.agents/workflows/plan-phase.md
@.agents/workflows/discuss-phase.md
@.agents/workflows/ui-phase.md
@.agents/workflows/add-phase.md
@.agents/workflows/insert-phase.md
@.agents/workflows/remove-phase.md
@.agents/workflows/plan-milestone-gaps.md
</execution_context>