request-refactor-plan

An interview-led planning process for structural refactors, such as renaming, moving, splitting, merging, deduplicating, or tightening types. It produces a sequence of small commits that should each leave the project working.

In plain words
What is it for?
Use it to plan a structural code change and optionally write the plan to the project's refactor-plans folder or create a GitHub issue.
Why use it?
It exposes affected callers, alternatives, scope limits, and test gaps before code is changed, without bundling new features or bug fixes into the refactor.

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

Made for: Claude Code, Codex.

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 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 $0.00080 $0.00831
Opus 5 $0.00040 $0.00415
Sonnet 5 $0.00016 $0.00166
Haiku 4.5 $0.00008 $0.00083

Measured 3d ago against content hash 83cbfec44cc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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

Copies of this mod

1 near-identical copy found in the catalogue:

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. 3d 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-codex-plugin (15 stars, last pushed 1mo 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. 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

apm-review-panel

Use this skill to run a multi-persona expert advisory review on a labelled pull request in microsoft/apm. The panel fans out to five mandatory specialists plus a test-coverage specialist (active on every PR that touches src/) plus three conditional specialists (auth, doc-writer, performance-expert), all running in…

microsoft/apm · 178 tokens

batch-bug-shepherd

Use this skill to drive a batch of suspected bugs in microsoft/apm from raw issue list to mergeable PR queue. Fan out one triage subagent per issue (LEGIT / UNCLEAR / FIXED-AT-HEAD), gate every legit bug against PRINCIPLES.md via an apm-ceo strategic-alignment pass, cross-reference legit issues against open PRs, then…

microsoft/apm · 227 tokens

apm-issue-autopilot

Use this skill to drive any open microsoft/apm issue (bug, feature, docs, refactor, perf) from raw intake to a mergeable PR with triage as the central, paramount gate. Run the apm-triage-panel rubric per issue first, then present ONE consolidated triage review for the whole batch and escalate to the maintainer BY…

microsoft/apm · 238 tokens

apm-spec-guardian

Use this skill to run a four-panel adversarial advisory review on any pull request that touches the OpenAPM specification artifact (docs/src/content/docs/specs/openapm-.md), its inline / sidecar JSON Schemas (docs/src/content/docs/specs/schemas/.schema.json), or the conformance fixture seed…

microsoft/apm · 215 tokens

apm-triage-panel

Use this skill to triage one microsoft/apm issue selected by the daily sweep, the status/needs-triage fast path, or manual dispatch. Emit one synthesized comment with a decision, label set, exact milestone, and suggested next action.

microsoft/apm · 59 tokens

cli-logging-ux

Use this skill when editing or creating CLI output, logging, warnings, error messages, progress indicators, or diagnostic summaries in the APM codebase. Activate whenever code touches console helpers (richsuccess, richwarning, richerror, richinfo, richecho), DiagnosticCollector, STATUSSYMBOLS, CommandLogger, or any…

microsoft/apm · 94 tokens