Plan mode

Skill mpuig/raw/builder/skills/plan-mode

Agent-native workflow orchestration platform that separates intelligence (agents) from infrastructure (state, logging, caching, retries)

Install

npx -y skills add mpuig/raw --skill plan-mode

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Guide for creating structured plans with numbered steps and quality gates

SKILL.md

1.9 KB, as published. Nobody here has run it

Plan Mode Skill

Use this skill when creating a plan for workflow implementation.

Plan Structure

Your plan MUST follow this structure:

1. Analysis

What needs to be done and why?
What is the current state vs. desired state?
What are the constraints or requirements?

2. Approach

High-level strategy for implementation
Key design decisions
Which patterns or libraries to use

3. Steps

Numbered, concrete steps (3-10 steps typically)
Each step should be specific and actionable
Include which files will be modified
Mention which tools/imports are needed
Consider dependencies between steps

4. Quality Gates

List gates that should pass after execution
Always include: validate, dry
Add optional gates if needed: pytest, ruff, typecheck

Example Plan

## Analysis
The workflow needs to fetch stock prices from Yahoo Finance API to provide
real-time data. Currently, there's no data fetching capability.

## Approach
We will create a new tool `yahoo_finance` in tools/ that wraps the yfinance
library, then integrate it into the workflow using a @step decorator.

## Steps
1. Create tools/yahoo_finance/tool.py with fetch_stock_price() function
2. Add yfinance dependency to tool's config.yaml
3. Update workflow run.py to import yahoo_finance
4. Add @step("fetch_prices") that calls yahoo_finance.fetch_stock_price()
5. Update dry_run.py with mock stock data for testing
6. Add test case in test.py for the fetch step

## Quality Gates
- validate: Structural validation must pass
- dry: Dry run with mocks must complete successfully
- pytest: All unit tests must pass

Tips

Keep steps atomic and sequential
Don't skip validation in your plan
Always consider the dry run path
Think about error cases and edge conditions
Reference existing code patterns when possible

Gives 0 of the 12 instructions most plan spec skills give

Counted across 1,100 of the 1,860 authors here whose files we hold, read 2026-08-06

ask one question at a timein 46 of 1100, across 38 files
Break plans into vertical slicesin 28 of 1100, across 10 files
Publish issues in dependency orderin 27 of 1100, across 9 files
Iterate until user approves the breakdownin 24 of 1100, across 6 files
Explore the repository to understand the codebase statein 24 of 1100, across 7 files
Use domain glossary vocabularyin 23 of 1100, across 5 files
Apply correct triage labels to published issuesin 23 of 1100, across 5 files
Write failing tests before implementation codein 23 of 1100, across 18 files
Prefer AFK slices over HITLin 22 of 1100, across 7 files
ask clarifying questions until requirements are concretein 21 of 1100, across 13 files
Respect existing architecture decision recordsin 20 of 1100, across 5 files
write a specification before writing any codein 20 of 1100, across 12 files

Said here and by no other author read

include an analysis section
include an approach section
include a steps section
include a quality gates section
number the steps
keep steps atomic and sequential

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.