feature-builder

A guided workflow for adding a new software feature, designed for someone with no coding experience. It turns a feature idea into a plan, file list, commands, testing steps, and a way to undo the changes.

In plain words
What is it for?
Use it to plan and implement a feature, especially when the request is vague or the user needs step-by-step guidance.
Why use it?
It reduces uncertainty by clarifying what to build, what will change, how to test it, and how to recover if something breaks.

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/emilyli2020/wave/feature-builder
Any agent
npx skills add emilyLi2020/WAVE --skill feature-builder
Clone the repo
git clone --depth 1 https://github.com/emilyLi2020/WAVE

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 445 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 $0.00047 $0.00445
Opus 5 $0.00023 $0.00222
Sonnet 5 $0.00009 $0.00089
Haiku 4.5 $0.00005 $0.00044

Measured 2d ago against content hash 8f7d0b45af16, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-builder 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.

.agents/skills/feature-builder/SKILL.md · 52 lines

What it actually says

Feature Builder

The user wants to implement a new feature. They have no coding background. Guide them through a structured, safe process.

Step 1: Understand the Feature

Ask the user to describe:

  • What the feature should do (in their own words)
  • Who will use it
  • What it should look like (screenshots, sketches, or descriptions are all fine)

If the description is vague, propose 2-3 concrete interpretations and ask which one is closest.

Step 2: Create the Plan

Generate a plan with exactly these sections:

  1. Goal: One sentence describing the feature
  2. Steps: 5-10 numbered steps, each with a single goal
  3. Files: List every file that will be created or changed
  4. Dependencies: Any new libraries needed (ask before installing)
  5. Commands: Copy-paste terminal commands to run
  6. Manual Test: Step-by-step instructions to verify the feature works
  7. Rollback Plan: How to undo the changes if something breaks

Step 3: Implement

  • Build the smallest vertical slice first: input > minimal processing > visible output
  • Implement one step at a time; confirm each step works before moving to the next
  • Use the simplest libraries and hosted services available
  • Target a visible, working demo in under 60 minutes

Step 4: Verify

After implementation:

  • Run the project and capture any errors
  • Walk the user through the manual test steps
  • If errors occur, explain them in plain English and propose fixes
  • Ask: "Does this match what you had in mind?"

Constraints

  • Never add features the user did not ask for
  • Never make changes outside the scope of this feature
  • Keep changes minimal, testable, and reversible
  • Prefer high-level libraries over low-level implementations
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 · 52 lines · 47 tokens per session scan A 8f7d0b45af16

Subscribe to this mod's changes

feature-builder is a skill published in the GitHub repository emilyLi2020/WAVE (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 445 once invoked, about $0.0002 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 2026-08-31.

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

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

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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