hamburger-method

A skill for splitting a large feature into small, complete delivery pieces using the Hamburger Method, a way to plan work in thin end-to-end slices.

In plain words
What is it for?
Identifying the layers of a feature, proposing several implementation choices for each layer, and composing minimal slices that can be delivered incrementally.
Why use it?
It helps when a feature is too large to deliver safely as one change and ordinary story-splitting does not make the boundaries clear.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nikeyes/stepwise-dev/hamburger-method
Any agent
npx skills add nikeyes/stepwise-dev --skill hamburger-method
Clone the repo
git clone --depth 1 https://github.com/nikeyes/stepwise-dev

Made for: Claude Code, Codex.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,513 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.02513
Opus 5 $0.00025 $0.01256
Sonnet 5 $0.00010 $0.00503
Haiku 4.5 $0.00005 $0.00251

Measured 2d ago against content hash fa63327872fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hamburger-method scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

core/skills/hamburger-method/SKILL.md · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hamburger Method - Vertical Story Slicing

Expert in applying the Hamburger Method (by Gojko Adzic) to break down large features into small, safe, deliverable vertical slices.

When to Use This Skill

Use when:

  • Feature feels large but not obviously splittable with story-splitting heuristics
  • User asks "how to slice" or "how to deliver incrementally"
  • Need to generate multiple implementation options
  • Want to compose end-to-end vertical slices

Do NOT use when:

  • Story has obvious "and", "or", "manage" indicators (use story-splitting instead)
  • User is asking HOW to implement (use micro-steps-coach instead)
  • Feature is already small (< 1 day work)

Core Process

When user describes a feature or story that needs slicing:

1. Identify Layers (Technical or Logical Steps)

Identify the main technical or business steps involved.

List 3-6 layers that form the complete flow.

Example for notification system:

  • Layer 1: Detect triggering event
  • Layer 2: Decide whom to notify
  • Layer 3: Format the message
  • Layer 4: Deliver the message
  • Layer 5: Record delivery status

2. Generate 4-5 Options per Layer

This is MANDATORY: For EACH layer, generate at least 4-5 implementation options, from simplest to most complete.

Use a numbered system: 1.1, 1.2, 1.3... for Layer 1, then 2.1, 2.2, 2.3... for Layer 2, etc.

Quality gradient (low to high):

  • Manual / hardcoded
  • Semi-automated / configurable
  • Fully automated / robust
  • Scalable / multi-channel
  • Enterprise-grade / resilient

Example for "Deliver the message" layer:

  • 4.1: Manual email from your personal account
  • 4.2: Scripted email via command line
  • 4.3: Email via SMTP service (no retries)
  • 4.4: Email via queuing system with retries
  • 4.5: Multi-channel (email, push, SMS) with fallbacks

3. Force Radical Slicing

Always ask this question out loud in your response — do not skip it:

"If you had to ship something by tomorrow, what would you build?"

Then answer it explicitly by naming the specific options (by number) you would pick from each layer. This forces the absolute minimum viable slice, not just a "simple version".

Read the full file on GitHub · 269 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 269 lines · 50 tokens per session scan A fa63327872fd

Subscribe to this mod's changes

hamburger-method is a skill published in the GitHub repository nikeyes/stepwise-dev (24 stars, last pushed 13d ago), licensed Apache-2.0. It adds 50 tokens to every session and 2,513 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens