Skill

plan-mega-review

The most thorough plan review possible. Three modes: SCOPE EXPANSION (dream big, build the cathedral), HOLD SCOPE (review what's here with maximum rigor), and SCOPE REDUCTION (strip to essentials). Context-dependent defaults, but when the user says EXPANSION -- go full send. Challenges premises, maps every failure mode, demands full observability, treats every edge case as a first-class citizen, and calls out specific errors and rescue paths by name. If the standard plan review is a 5, HOLD SCOPE is an 8, and EXPANSION is a 15. Boil the ocean. See around corners. Leave nothing unquestioned. Credit: Garry Tan (https://gist.github.com/garrytan/120bdbbd17e1b3abd5332391d77963e7)

npx claudepluginhub tangle-network/skills --plugin plan-mega-review

Tool Access

This skill is limited to using the following tools:

ReadGrepGlobBashAskUserQuestion

Preview

Use this skill when the user asks for a plan review, architecture review, or says

Supporting Assets

references/garrys-mega-plan.md

SKILL.md

Similar Skills

cache-components

139.3k

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

mcp-builder

124.2k

Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).

9 files

anthropics-skills-13

canvas-design

124.2k

Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.

20 files

anthropics-skills-13

Stats

Parent Repo Stars0

Parent Repo Forks0

Last CommitMar 7, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

plan-mega-review

Garry Tan's Mega Plan Review Mode

Trigger

Use this skill when the user asks for a plan review, architecture review, or says "review this plan", "mega review", "plan review", or similar.

Required Reading

Read references/garrys-mega-plan.md for the full review methodology before proceeding.

Quick Summary

Three review modes:

SCOPE EXPANSION -- Dream big. Push scope up. Build the cathedral.

HOLD SCOPE -- Rigorous review. Make the existing plan bulletproof.

SCOPE REDUCTION -- Strip to essentials. Cut everything non-critical.

Process

Run PRE-REVIEW SYSTEM AUDIT (git log, diff, stash, TODOs)

Step 0: Nuclear Scope Challenge + Mode Selection (STOP and ask user)

10 review sections, each with a STOP gate:

Architecture, Error/Rescue Map, Security, Data/UX Edge Cases, Code Quality, Tests, Performance, Observability, Deployment, Long-Term

Required outputs: Error registry, failure modes, diagrams, TODOS.md updates

Prime Directives

Zero silent failures

Every error has a name

Data flows have shadow paths (nil, empty, error)

Interactions have edge cases

Observability is scope, not afterthought

Diagrams are mandatory

Everything deferred must be written down

Optimize for 6-month future

Permission to say "scrap it and do this instead"