request-refactor-plan

request-refactor-plan is a skill for Claude Code, Codex from OutlineDriven/odin-gemini-cli-extension. It costs 80 tokens per session (831 once invoked), scanned A, a copy of request-refactor-plan, Apache-2.0.

A workflow for planning structural code changes, such as renaming, moving, extracting, splitting, or deduplicating code, without changing behavior.

In plain words
What is it for?
Use it to create a Markdown refactor plan and optionally a GitHub issue, including alternatives, scope boundaries, affected code, and tests.
Why use it?
It turns a large refactor into small commits that keep the code working. It also checks the actual codebase and test coverage before the plan is written.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/outlinedriven/odin-gemini-cli-extension/request-refactor-plan
Any agent
npx skills add OutlineDriven/odin-gemini-cli-extension --skill request-refactor-plan
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/odin-gemini-cli-extension

Made for: Claude Code, Codex.

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 request-refactor-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/request-refactor-plan.svg)](https://agentmods.dev/skills/outlinedriven/odin-gemini-cli-extension/request-refactor-plan)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/odin-gemini-cli-extension/request-refactor-plan"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/request-refactor-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 831 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00080 $0.00831
Opus 5 $0.00040 $0.00415
Sonnet 5 $0.00016 $0.00166
Haiku 4.5 $0.00008 $0.00083

Measured 6d ago against content hash 83cbfec44cc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

request-refactor-plan 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.

Origin

This is a copy

100% identical to request-refactor-plan — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/request-refactor-plan/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial interview to break a refactor into the smallest commits that each leave the codebase green.

Scope fence

Refactor-plan is structural-only and scope-narrow: rename, extract, move, split, merge, dedupe, type-tighten, dependency invert. No behavior change. No new features. No bug fixes bundled in.

For general feature work or behavior change, use general implementation planning. For executing a refactor that intentionally breaks compat, use the break-compat refactor workflow.

Output

Default: write plan to <project-root>/docs/refactor-plans/<kebab-name>.md.

Optional --emit-issue: after writing the file, also file a GitHub issue with gh issue create --body-file <path>.

Interview protocol (linear)

  1. Solicit a long description of the perceived problem and any sketched solutions. Do not act yet.
  2. Dispatch Explore agent to verify the user's claims against the actual code; produce a structural map of the affected surface.
  3. Confront with alternatives. List 2-3 options with concrete trade-offs and a recommendation.
  4. Pin scope explicitly. Enumerate what changes AND what stays untouched.
  5. Audit test coverage of the affected surface. Use git grep -l for callsite-adjacent assertions, plus extension-and-glob test discovery: fd -g '*.test.ts' -g '*.spec.ts' (Node), fd -g '*_test.go' (Go), fd -g 'test_*.py' -g '*_test.py' (Python), fd -g '*_test.rs' plus git grep -n '#\[test\]' (Rust), fd -g 'test_*.ml' -g '*_test.ml' (OCaml).
  6. Decompose into the smallest commits where each leaves the tree green. Fowler's rule: "make each refactoring step as small as possible."
  7. Write the plan file using the template below.
  8. If --emit-issue was passed, mirror to GitHub.

Plan file template

# Refactor: <name>

## Problem
<developer's framing of the pain>

## Solution
<chosen approach in one paragraph>

## Commits
<numbered list; each commit is one concern; each leaves the tree green; plain English, no file paths>

## Decisions
- modules touched
- interfaces modified
- schema/API contract changes
- explicit non-decisions

## Testing
- what counts as a good test (external behavior, not internals)
- modules under test
- prior-art tests in the repo

## Out of scope
<explicit non-goals>

Read the full file on GitHub · 67 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 · 67 lines · 80 tokens per session scan A 83cbfec44cc4

Subscribe to this mod's changes

request-refactor-plan is a skill published in the GitHub repository OutlineDriven/odin-gemini-cli-extension (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 831 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to request-refactor-plan, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

request-refactor-plan

Plan a refactor as a sequence of tiny, working commits via adversarial interview. Default output is a markdown plan at /docs/refactor-plans/ .md; pass --emit-issue to also file a GitHub issue. Trigger on structural refactors (rename, extract, move, split, dedupe) — NOT new features.

OutlineDriven/odin-codex-plugin · 80 tokens

setup-pre-commit

Install git pre-commit hooks via the project's hook tool — Husky+lint-staged (JS), pre-commit (Python/OCaml), lefthook (Go), cargo-husky (Rust). Use when the user wants commit-time formatting, linting, type-checking, or test gates. Detects ecosystem first.

OutlineDriven/odin-codex-plugin · 73 tokens

atomic-commit-and-push

Run the atomic-commit workflow on the current changes, then publish the resulting commits to the remote. Use whenever the user says "commit and push", "ship these changes", "atomic commit and push", "publish my work", or wants atomic commits delivered to origin in one step. Prefers git submit (git-branchless); falls…

OutlineDriven/odin-codex-plugin · 111 tokens

atomic-commit

Review staged + unstaged changes and split them into one commit per logical change. Use whenever the user says "atomic commit", "commit my changes", "split this into commits", or has multiple unrelated edits sitting in the working tree — even if they don't say "atomic". Runs repo-native type-checker and linter before…

OutlineDriven/odin-codex-plugin · 78 tokens

git-branchless

Enforce idiomatic git-branchless during planning and executing tasks — detached-HEAD-first work, in-memory rebase via git move, event-log recovery via git undo, deferred branch creation, speculative-merge git sync for base updates. Use when planning or executing multi-commit work, history rewrites, stack edits…

OutlineDriven/odin-codex-plugin · 131 tokens

qa

Conversational QA mode — user reports bugs in plain language, agent clarifies minimally, files GitHub issues that survive refactors. Trigger on "QA", "QA session", or ad-hoc bug reporting without a fixed deliverable shape. Distinct from branch-scoped and PR-scoped review.

OutlineDriven/odin-codex-plugin · 62 tokens