refactor-feature

refactor-feature is a skill for Claude Code from DGouron/review-flow. It costs 41 tokens per session (1,965 once invoked), scanned A, original, MIT.

A workflow for safely changing existing software through written specifications, contract tests, and small implementation batches. TDD means writing tests around the required behavior as part of development.

In plain words
What is it for?
Use it to plan and coordinate refactors, modify or remove existing code in batches, run regression checks, and track the work in documentation.
Why use it?
Changing existing code can break current users even when the new behavior works; this process checks existing contracts and regression risks as work progresses.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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/dgouron/review-flow/refactor-feature
Any agent
npx skills add DGouron/review-flow --skill refactor-feature
Clone the repo
git clone --depth 1 https://github.com/DGouron/review-flow

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for refactor-feature

README.md
[![agentmods](https://agentmods.dev/badge/skills/dgouron/review-flow/refactor-feature.svg)](https://agentmods.dev/skills/dgouron/review-flow/refactor-feature)
Your own site
<a href="https://agentmods.dev/skills/dgouron/review-flow/refactor-feature"><img src="https://agentmods.dev/badge/skills/dgouron/review-flow/refactor-feature.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,965 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 5.1 $0.00041 $0.01965
Opus 5 $0.00020 $0.00983
Sonnet 5 $0.00008 $0.00393
Haiku 4.5 $0.00004 $0.00197

Measured 6d ago against content hash a79771be9f78, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

refactor-feature 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 6d 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/refactor-feature/SKILL.md · 294 lines

How it starts

The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactor Feature — Spec-Driven Refactoring Orchestrator

Role

You are the orchestrator of a spec-driven refactoring pipeline. You coordinate two agents to modify existing code safely, with tests, incrementally.

You do NOT code yourself. You coordinate, present, and validate with the user.

Difference with /implement-feature

Aspect /implement-feature /refactor-feature
Goal Create code from scratch Modify/delete existing code
Key phase TDD inside-out (RED first) Contract tests (GREEN first)
Plan Files to create by layer Files to modify/delete, by batch
Progression Final report Incremental tracking in docs/refactor/
Main risk "it doesn't work" Regression on existing consumers

Agents

Agent Role Skills preloaded
feature-planner Analyzes the spec, produces a refactoring plan by batch clean-architecture
feature-implementer Implements modifications with TDD, self-review tdd, clean-architecture

Skills consumed

Skill What we use Phase
/refactoring Methodology (Mikado / Strangler Fig), tracking file structure, batch workflow Phase 0 (method choice) + Phase 2 (tracking)
/tdd RED-GREEN-REFACTOR cycle. In Phase 1, twist: GREEN first instead of RED first Phase 1 (contract tests) + Phase 3 (implementation)

Input

The user provides either:

  • A path to a spec: /refactor-feature docs/specs/my-refactoring.md
  • A GitHub issue: /refactor-feature #42
  • An inline description

If the spec is vague or missing, suggest /product-manager to structure it.


Workflow

Phase 0: LOAD SPEC + CHOOSE METHOD

  1. Read the spec (file or GitHub issue)
  2. Read the current code of main impacted files
  3. Choose the method (/refactoring conventions):
    • Strangler Fig if old code must stay functional during migration
    • Mikado if dependencies are complex to untangle
    • Import swap if it's a simple import replacement (sub-case of Strangler)
    • Ask the user if not obvious
  4. Display a summary:

Read the full file on GitHub · 294 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. 6d ago First seen · 294 lines · 41 tokens per session scan A a79771be9f78

Subscribe to this mod's changes

refactor-feature is a skill published in the GitHub repository DGouron/review-flow (42 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 1,965 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 2026-08-30.

Related

Other skills, from other repositories

selecting-vizro-charts

Use this skill when choosing chart types, applying Plotly Express conventions, configuring colors, building KPI cards, or adding tables (AG Grid) to Vizro dashboards. Activate when the user asks which chart fits their data, needs custom chart functions, wants to set colors or palettes, is creating KPI metric cards, or…

mckinsey/vizro · 78 tokens

verify-changes

Verify a code change in this repo before committing or opening a PR. Use after editing collector (backend), web (frontend), shared package, or the Go agent — picks the minimal sufficient check set per touched area.

foru17/neko-master · 47 tokens

new-skill

Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…

hyhmrright/brooks-lint · 145 tokens

monitor-webcams

Discover live webcams in a map viewport and resolve thumbnails or player URLs. Use when the user asks for visual context near a location, route, border, port, or city.

koala73/worldmonitor · 39 tokens

track-tariff-trends

Retrieve MFN applied tariff-rate timeseries for a reporting country — applied vs bound rates by year, plus the optional US effective tariff rate. Use when the user asks how a country's MFN tariffs have changed over time.

koala73/worldmonitor · 51 tokens

architecture-patterns

Architecture validation and patterns for clean architecture, backend structure enforcement, project structure validation, test standards, and context-aware sizing. Use when designing system boundaries, enforcing layered architecture, validating project structure, defining test standards, or choosing the right…

yonatangross/orchestkit · 56 tokens