model planning workflow risk: low

Coding Task Plan Generator

Instructs the model to create a concise, actionable plan for coding tasks by scanning context, asking minimal follow-up questions if blocking, and outputting in a specific markdown…

PROMPT

---
name: create-plan
description: Create a concise plan. Use when a user explicitly asks for a plan related to a coding task.
metadata:
  short-description: Create a plan
---

# Create Plan

## Goal

Turn a user prompt into a **single, actionable plan** delivered in the final assistant message.

## Minimal workflow

Throughout the entire workflow, operate in read-only mode. Do not write or update files.

1. **Scan context quickly**
   - Read `README.md` and any obvious docs (`docs/`, `CONTRIBUTING.md`, `ARCHITECTURE.md`).
   - Skim relevant files (the ones most likely touched).
   - Identify constraints (language, frameworks, CI/test commands, deployment shape).

2. **Ask follow-ups only if blocking**
   - Ask **at most 1–2 questions**.
   - Only ask if you cannot responsibly plan without the answer; prefer multiple-choice.
   - If unsure but not blocked, make a reasonable assumption and proceed.

3. **Create a plan using the template below**
   - Start with **1 short paragraph** describing the intent and approach.
   - Clearly call out what is **in scope** and what is **not in scope** in short.
   - Then provide a **small checklist** of action items (default 6–10 items).
      - Each checklist item should be a concrete action and, when helpful, mention files/commands.
      - **Make items atomic and ordered**: discovery → changes → tests → rollout.
      - **Verb-first**: “Add…”, “Refactor…”, “Verify…”, “Ship…”.
   - Include at least one item for **tests/validation** and one for **edge cases/risk** when applicable.
   - If there are unknowns, include a tiny **Open questions** section (max 3).

4. **Do not preface the plan with meta explanations; output only the plan as per template**

## Plan template (follow exactly)

```markdown
# Plan

<1–3 sentences: what we’re doing, why, and the high-level approach.>

## Scope
- In:
- Out:

## Action items
[ ] <Step 1>
[ ] <Step 2>
[ ] <Step 3>
[ ] <Step 4>
[ ] <Step 5>
[ ] <Step 6>

## Open questions
- <Question 1>
- <Question 2>
- <Question 3>
```

## Checklist item guidance
Good checklist items:
- Point to likely files/modules: src/..., app/..., services/...
- Name concrete validation: “Run npm test”, “Add unit tests for X”
- Include safe rollout when relevant: feature flag, migration plan, rollback note

Avoid:
- Vague steps (“handle backend”, “do auth”)
- Too many micro-steps
- Writing code snippets (keep the plan implementation-agnostic)

REQUIRED CONTEXT

user coding task prompt
codebase context (README.md, docs/, relevant files)

ROLES & RULES

Operate in read-only mode.
Do not write or update files.
Ask follow-ups only if blocking.
Ask at most 1–2 questions.
Prefer multiple-choice questions.
Make reasonable assumptions if not blocked.
Start plan with 1 short paragraph describing intent and approach.
Clearly call out in scope and out of scope.
Provide small checklist of 6–10 action items.
Make checklist items atomic and ordered: discovery → changes → tests → rollout.
Use verb-first in checklist items.
Include at least one item for tests/validation.
Include item for edge cases/risk when applicable.
Include Open questions section only if unknowns (max 3).
Do not preface plan with meta explanations.
Output only the plan as per template.
Avoid vague steps.
Avoid too many micro-steps.
Avoid writing code snippets.

EXPECTED OUTPUT

Format

markdown

Schema

markdown_sections · Plan, Scope, Action items, Open questions

Constraints

follow exact plan template
1-3 sentences intro
Scope: In/Out
Action items: 6-10 atomic ordered checklist items
Open questions: max 3 if needed
no meta explanations, output only the plan

SUCCESS CRITERIA

Turn user prompt into single actionable plan.
Follow plan template exactly.
Include scope in/out.
Provide 6–10 concrete checklist items.
Ensure items are atomic, ordered, verb-first.
Include tests/validation and edge cases when applicable.

FAILURE MODES

Prefacing with meta explanations.
Outputting anything besides the plan.
Using vague or non-atomic steps.
Including code snippets.
Writing or updating files.
Asking too many or unnecessary questions.
Incorrect template structure.

CAVEATS

Dependencies

Requires user prompt for coding task.
Requires README.md and relevant repo files/docs.

Missing context

Specific coding task from user.
Method for accessing/scanning repo files (e.g., tools or provided context).

Ambiguities

Assumes access to repo files (e.g., README.md) without specifying mechanism (tools, provided context).
'Blocking' threshold for follow-up questions is subjective.

QUALITY

OVERALL: 0.91
CLARITY: 0.92
SPECIFICITY: 0.95
REUSABILITY: 0.88
COMPLETENESS: 0.90

IMPROVEMENT SUGGESTIONS

Add placeholder for user task, e.g., 'User task: {task_description}'.
Explicitly define 'blocking' with examples: 'e.g., unclear requirements vs. minor assumptions'.
Include guidance on handling no open questions: 'Omit section if none'.
Specify repo context provision method.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.