five-step-method

A five-step decision framework for checking whether action is needed before deciding how to take it.

In plain words
What is it for?
Use it to assess requests, feedback, bug fixes, workflow changes, hiring or tool decisions, reviews, roadmaps, and deployment issues.
Why use it?
It helps prevent unnecessary features, fixes, meetings, tools, and process changes by questioning the underlying need first.

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/agidesigner/five-step-method-skill/five-step-method
Any agent
npx skills add agidesigner/five-step-method-skill --skill five-step-method
Clone the repo
git clone --depth 1 https://github.com/agidesigner/five-step-method-skill

Made for: Claude Code, Codex.

Per session 260 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,371 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 $0.00260 $0.02371
Opus 5 $0.00130 $0.01185
Sonnet 5 $0.00052 $0.00474
Haiku 4.5 $0.00026 $0.00237

Measured 2d ago against content hash 72bef86da853, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

five-step-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.

.claude/skills/five-step-method/SKILL.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Five-Step Work Method

A universal decision framework that teaches you to evaluate whether to act before deciding how to act. Apply this to any decision — code, product, strategy, process, hiring, meetings, or resource allocation.

When to Apply

Trigger Action
New feature / product request Must apply — Question need before designing
External feedback (multiple points) Must apply — Evaluate each point independently
Bug fix that requires > 10 lines Must apply — Question if the fix adds complexity
Process / workflow change proposal Must apply — Can we delete the process instead?
New tool / vendor / hire decision Must apply — Is the role/tool actually needed?
Meeting or review request Must apply — Can this be an async message?
Strategy / roadmap planning Must apply — Delete low-impact items first
Configuration / deployment issue Must apply — Ask if code change is even needed
Single-line typo or obvious fix Skip — Just fix it
User gives explicit instructions Skip — Follow instructions, then review

The Five Steps

Step 1: Question the Requirement

Ask: "Is this actually needed? What happens if we don't do it?"

  • Challenge every request, including your own instincts
  • Check if the problem solves itself (e.g., agent self-corrects after retry)
  • Distinguish "nice to have" from "actually broken"
  • Ask who benefits and how often
  • If only one user hit it once, it's probably not a product problem

Decision matrix:

Frequency Impact Action
Common + High Do it Proceed to Step 2
Common + Low Maybe Proceed to Step 2
Rare + High Record Log for later, don't code now
Rare + Low Skip Don't do it

Step 2: Delete

Remove what shouldn't exist before adding anything.

  • Delete the feature, code, or process that created the problem
  • Delete options when a sensible default works
  • Delete fallbacks when the primary path is reliable
  • Delete auto-detection when one config line suffices
  • Delete backwards-compatibility shims for things nobody uses

Read the full file on GitHub · 213 lines

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 · 213 lines · 260 tokens per session scan A 72bef86da853

Subscribe to this mod's changes

five-step-method is a skill published in the GitHub repository agidesigner/five-step-method-skill (20 stars, last pushed 4mo ago), licensed MIT. It adds 260 tokens to every session and 2,371 once invoked, about $0.0013 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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens