Agent skill

Omh Refactor Plan

by rlaope in rlaope/oh-my-hermes

[omh] Decided cross-module refactor to phase: refactor planning - turn a decided boundary-changing refactor into a phased plan - reconnaissance, contracts-first phase order, per-phase verification…

MITAuto-check passedDevelopment

Install Omh Refactor Plan

skills CLI
$ npx skills add rlaope/oh-my-hermes --skill omh-refactor-plan -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install rlaope/oh-my-hermes omh-refactor-plan --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/rlaope/oh-my-hermes.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/omh-refactor-plan .claude/skills/omh-refactor-plan && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
omh-refactor-plan
GitHub stars
3.2k
Token cost
~2.2k tokens
SKILL.md length
1,167 words
Files
3 (incl. references)
Skills in repo
143
Repo updated
First seen
Licence
MIT

At a glance

[omh] Decided cross-module refactor to phase: refactor planning - turn a decided boundary-changing refactor into a phased plan - reconnaissance, contracts-first phase order, per-phase verification…

  • The user says: refactor-plan
  • SKILL.md covers Why This Exists, Do Not Use When, Examples and Completion Checklist, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Plan this refactor

What it does

Omh Refactor Plan is an agent skill from rlaope/oh-my-hermes. [omh] Decided cross-module refactor to phase: refactor planning - turn a decided boundary-changing refactor into a phased plan - reconnaissance, contracts-first phase order, per-phase verification and rollback, a files table, and an explicit approval gate before any edit. Use when the user says: refactor-plan, refactor plan, plan this refactor, plan the refactor, refactor planning, refactor phases, phased refactor, refactor in phases.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/dependency-upgrade.md` and `references/refactor-phases.md`).

It sits in Development, covering Refactoring. The repository describes itself as: All in one plugin for Hermes Agent ⚚ the coding intelligence, a long-term memory system and model optimized workflow packages. The licence is MIT.

When your agent uses it

  • The user says: refactor-plan
  • Plan this refactor
  • Plan the refactor
  • Refactor planning

Example prompts

  • “/omh-refactor-plan”

What it can do on your machine

Read from SKILL.md and the folder at commit 41de9dc. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Omh Refactor Plan loads about 2.2k tokens when it runs, and up to ~4.3k if it reads all its reference files. Until then it costs about 114 tokens; SKILL.md has 1,167 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~114
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from rlaope/oh-my-hermes at commit 41de9dc, republished under its MIT licence (© rlaope). 1,167 words, ~2,212 tokens.

Download SKILL.mdSave it as .claude/skills/omh-refactor-plan/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
omh-refactor-plan
description
[omh] Decided cross-module refactor to phase: refactor planning - turn a decided boundary-changing refactor into a phased plan - reconnaissance, contracts-first phase order, per-phase verification and rollback, a files table, and an explicit approval gate before any edit. Use when the user says: refactor-plan, refactor plan, plan this refactor, plan the refactor, refactor planning, refactor phases, phased refactor, refactor in phases.

Refactor Plan

This is a Hermes-native refactor-plan workflow skill.

Why This Exists

refactor-plan exists because boundary-changing refactors bounced between goal planning and behavior-preserving cleanup with neither owning the execution shape: the phase order, the per-phase rollback, and the files table that make a large refactor reviewable and abortable.

Do Not Use When

  • The refactor's direction is still contested or the goal itself needs consensus planning; use ralplan.
  • The work is deletion-first cleanup with no boundary changes; use ai-slop-cleaner.
  • The plan is done and the claim is that work is complete; use verification-gate for the evidence close.
  • The version bump carries a security advisory, a CVE, or a leaked secret; use security-event-response, which owns containment and closure.

Examples

Good example:

  • Prompt: We decided to split the billing module out of orders - plan the refactor so each step is shippable.
  • Expected behavior: Map affected files and consumers from the import graph, name hidden coupling and blast radius, order the five phases with per-phase verification and rollback, ship the files table, and stop at the approval gate.
  • Why: The direction is decided and the need is a phased, abortable execution shape - exactly this workflow's territory.

Bad example:

  • Prompt: Should we even split billing out of orders?
  • Expected behavior: Route to ralplan: the direction is not decided, so consensus planning comes before phase planning.
  • Why: A phase plan for a contested direction launders a decision through logistics.

Completion Checklist

  • Reconnaissance names affected files, boundaries, coupling, and blast radius from observed evidence.
  • Every phase carries its verification command and its rollback point, and ends at a shippable commit.
  • The files table covers every touched file with action, phase, and dependencies.
  • For an upgrade, every breaking change row names its call sites or an observed empty search, and every stage names its rollback.
  • The plan stopped at the approval gate; no implementation began without the user's go.

Recovery Notes

  • If the import graph is unavailable, build the codegraph first or reduce the plan's confidence and say which files are unverified.
  • If a phase cannot be made independently green, split it further; two half-phases beat one unabortable one.
  • If reconnaissance finds the direction itself is unsettled, route back to ralplan before ordering phases.

Workflow Lane

  • Current lane: Intent -> plan (oh-my-hermes, meta-router, deep-interview, context, plan, ralplan, adversarial-consensus, codebase-onboarding, +8 more) - clarify, plan, ship, or loop goals.
  • If intent belongs to another lane, hand back to oh-my-hermes or name the adjacent workflow.
  • Shared product, routing, compatibility, and evidence rules: omh-routing/references/skill-common-rail.md.

Use When

Use when a refactor that crosses module boundaries is already decided and needs its execution shaped: which files move in which phase, what verifies each phase, and where each phase rolls back to - before anything is edited.

Strong routing signals: `refactor-plan`, `refactor plan`, `plan this refactor`, `plan the refactor`, `refactor planning`, `refactor phases`, `phased refactor`, `refactor in phases`, `refactor rollback plan`, `blast radius`, `module restructure plan`, `restructure plan`, `dependency upgrade`, `major version upgrade`, `framework upgrade`, `upgrade to the next major`, `breaking change upgrade`, `lockfile`, `리팩터링 계획`, `리팩토링 계획`, `리팩터링 단계`, `단계별 리팩터링`, `리팩터링 계획 세워줘`, `리팩터링 롤백 계획`

Catalog Metadata

Category: planning Phase: refactor-plan Hermes role: planner Quality tier: plan-gated Reasoning demand: standard

Quality bar:

  • Reconnaissance first: affected files, ownership boundaries, hidden coupling, and blast radius are mapped before any phase is ordered; the full contract is omh-refactor-plan/references/refactor-phases.md.
  • Order phases contracts-first: types and interfaces, then implementations, then callers in reviewable groups, then tests, then cleanup - and name what verifies each phase and where it rolls back to.
  • Ship the files table with the plan: one row per file with action, phase, and blocks/blocked-by; a row without a phase is unplanned work.
  • Size verification to the blast radius, not to optimism: a phase touching public surfaces or persisted shapes carries the full gate, not the fast one.
  • For a dependency or framework upgrade, read four inputs before ordering phases — advisory and end-of-life intake, the licence delta at the target version, the upstream migration guide item by item against this codebase, and lockfile handling in the same commit as the manifest; a breaking change nobody checked is a gap, not a pass. The full contract is omh-refactor-plan/references/dependency-upgrade.md.
  • Stop at the approval gate and hand the user the go/no-go, whole plan or first phase.

Handoff policy:

Hermes owns reconnaissance and the phased plan; implementation of any approved phase is coding work for the selected executor lane under its own evidence rules. An approved plan is approval of the order, not evidence any phase ran.

Show full SKILL.md (423 more words)Show less

Required inputs:

  • the decided target shape (what moves where), or a pointer to the accepted plan that decided it
  • the affected-file evidence: import graph, codegraph handoff, or an observed file inventory
  • the regression gates that exist today (test suite, typecheck, generated-artifact checks)

Expected outputs:

  • reconnaissance: affected files, ownership boundaries, hidden coupling, blast radius — and for an upgrade, the advisory, licence, migration-guide, and lockfile intake
  • phase plan in the fixed order - types/interfaces, implementations, callers, tests, cleanup - each with verification and rollback
  • files table: path, action, phase, blocks/blocked-by
  • for an upgrade, the call-site readiness gate: every breaking change between the two versions against this repository's call sites or an observed empty search, and every stage's rollback
  • the approval gate: the plan stops and waits for the user's go

Artifact expectations:

  • metadata-only runtime record when a wrapper or shell is available

Safety rules:

  • The plan comes from observed repo evidence, never from memory of the tree.
  • An upgrade plan is not ready while any breaking change lacks its call sites or an observed empty search, or any stage lacks its rollback; name the open rows instead of calling the bump safe to merge.
  • Every phase ends at a commit that could ship; a phase that cannot end green is split further.
  • Nothing is deleted before the cleanup phase, and cleanup starts from a tagged rollback point.
  • Do not begin implementing any phase without the user's explicit approval of the plan.

Runtime Evidence

Record observed delegation results; otherwise return not_available or not_observed. Prepared OMH routing is not execution, review, CI, merge-readiness, or merge evidence.

  • Treat wrapper memory/context summaries as advisory local context, not proof of opaque Hermes memory reads or changes. Preserve workflow intent and stop conditions; verify before claiming completion. Reply in the user's own words and the host's own voice: its SOUL.md persona owns reply language, tone, speech level, and sentence endings, progress updates included (where it sets no language, use the one the user wrote in), and OMH shapes structure and content only; OMH's record terms (surface, lane, wrapper, handoff, evidence boundary, not_observed) stay in records and tool calls, never in the sentence the user reads unless they ask about one; and when a stop condition or a decision the user owns ends the turn, offer the next action as a question rather than declaring what will not be done.

Use Hermes-native subagent/delegation features when available: native subagents -> Hermes delegation when available, otherwise sequential lanes.

Shared product, compatibility, topology, memory, harness, and execution rules: omh-routing/references/skill-common-rail.md. Load it when applicable; otherwise name an unavailable capability.

© rlaope, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/omh-refactor-plan of rlaope/oh-my-hermes.

  • SKILL.md
  • references/dependency-upgrade.md
  • references/refactor-phases.md

Open the folder on GitHubat commit 41de9dc

Compare with similar skills

Omh Refactor Plan next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Omh Refactor Plan compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Omh Refactor Plan this skillrlaope/oh-my-hermes3.2k—~2.2kAutomated safety check: PassMIT
Goinference-gateway/inference-gateway214—~2.4kAutomated safety check: PassApache-2.0
Software Design Reviewatilladeniz/Kubeli387—~5.3kAutomated safety check: PassMIT
Nv Endpoint Routed Tool Providernovuhq/novu40k—~2.8kAutomated safety check: PassCustom licence
Rollback Changesmaslennikov-ig/claude-code-orchestrator-kit260—~760Automated safety check: NotesCustom licence
Antislop Codebaseswyxio/skills175—~1.6kAutomated safety check: PassMIT

Similar skills

  • Go

    inference-gateway/inference-gateway

    Idiomatic Go - package and interface design, error wrapping, table-driven tests, generics, the modern standard library (slices/maps/cmp/errors.Join), current syntax, and logging discipline.

    214 GitHub stars~2.4k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Software Design Review

    atilladeniz/Kubeli

    Analyzes code based on John Ousterhout's "A Philosophy of Software Design".

    387 GitHub stars~5.3k tokensUpdated 4 days ago
    DevelopmentAuto-check passed
  • Build or refactor a Tool-channel provider (PagerDuty, Opsgenie, future incident/alerting tools) to be endpoint-routed: per-subscriber secrets encrypted on the channel endpoint resource, a stateless…

    40k GitHub stars~2.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Rollback Changes

    maslennikov-ig/claude-code-orchestrator-kit

    Automatically rollback changes from failed workflow phases using changes log files.

    260 GitHub stars~760 tokensUpdated 7 mo ago
    DevelopmentAuto-check: notes
  • Antislop Codebase

    swyxio/skills

    Diagnose or execute an explicit repository-wide maintainability cleanup while preserving behavior.

    175 GitHub stars~1.6k tokensUpdated 5 days ago
    DevelopmentAuto-check passed
  • Effect TS

    pproenca/dot-skills

    Effect-TS library usage in TypeScript — Effect.gen generators, Schema.Struct/Schema.Class definitions, Layer/Context.Tag/Service patterns, Effect.pipe pipelines, Data.TaggedError/Data.Class error…

    215 GitHub stars~2k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from rlaope/oh-my-hermes

All 143 skills in this repo
  • Omh Accessibility Audit

    rlaope/oh-my-hermes

    [omh] Screen-reader or keyboard accessibility gaps: prepare WCAG, keyboard, focus, screen-reader, target-size, and reflow evidence gates for UI surfaces.

    3.2k GitHub stars~2.8k tokensUpdated yesterday
    Auto-check passed
  • Omh Agent Evaluation

    rlaope/oh-my-hermes

    [omh] Choosing between coding agents on evidence: compare executor or agent choices on reproducible tasks using quality, cost, time, tool, and evidence metrics.

    3.2k GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed
  • Omh Agent Instructions

    rlaope/oh-my-hermes

    [omh] Agent instruction file for a repo -- AGENTS.md, CLAUDE.md, a Cursor rule: write or update what an agent cannot derive from the code, inside a marked region, with every command verified or…

    3.2k GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed
  • Omh Agent Ops Review

    rlaope/oh-my-hermes

    [omh] AI agent progress for managers: help managers inspect AI-agent progress, blockers, quality gates, and throughput levers.

    3.2k GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • Omh AI Slop Cleaner

    rlaope/oh-my-hermes

    [omh] Messy or AI-generated code to clean up: delete AI-generated slop, dead code, and duplication while observable behavior stays identical.

    3.2k GitHub stars~2.7k tokensUpdated yesterday
    Auto-check passed
  • Omh App Debugging

    rlaope/oh-my-hermes

    [omh] Application code misbehaves -- a wrong value, a flaky test, a lost update: reproduce it first, form competing hypotheses, discriminate them with the cheapest observation, and only then fix the…

    3.2k GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed

Questions about Omh Refactor Plan

What does Omh Refactor Plan do?

[omh] Decided cross-module refactor to phase: refactor planning - turn a decided boundary-changing refactor into a phased plan - reconnaissance, contracts-first phase order, per-phase verification…. Omh Refactor Plan is an agent skill from rlaope/oh-my-hermes. [omh] Decided cross-module refactor to phase: refactor planning - turn a decided boundary-changing refactor into a phased plan - reconnaissance, contracts-first phase order, per-phase verification and rollback, a files table, and an explicit approval gate before any edit.

When should I use Omh Refactor Plan?

Omh Refactor Plan fits situations like: the user says: refactor-plan; plan this refactor; plan the refactor; refactor planning.

How do I install Omh Refactor Plan in Claude Code?

Run `npx skills add rlaope/oh-my-hermes --skill omh-refactor-plan -a claude-code`. Or copy the skill folder (skills/omh-refactor-plan in rlaope/oh-my-hermes) into .claude/skills/omh-refactor-plan in your project. Claude Code loads it when a task matches its description.

How do I install Omh Refactor Plan in Codex?

Run `npx skills add rlaope/oh-my-hermes --skill omh-refactor-plan -a codex`. Or copy the skill folder (skills/omh-refactor-plan in rlaope/oh-my-hermes) into .agents/skills/omh-refactor-plan in your project. Codex loads it when a task matches its description.

Can I use Omh Refactor Plan in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rlaope/oh-my-hermes --skill omh-refactor-plan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/omh-refactor-plan, .gemini/skills/omh-refactor-plan, .github/skills/omh-refactor-plan and .opencode/skills/omh-refactor-plan in your project.

What does Omh Refactor Plan need to run?

SKILL.md names no scripts, command-line tools or credentials: Omh Refactor Plan is instructions for the agent only.

Does Omh Refactor Plan access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Omh Refactor Plan safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Omh Refactor Plan use?

Omh Refactor Plan is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Omh Refactor Plan use?

About 2.2k tokens (SKILL.md is roughly 8.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.1k tokens, read only when the agent opens those files.

What are the alternatives to Omh Refactor Plan?

Skills that share tags, products or a category with Omh Refactor Plan: Go (inference-gateway/inference-gateway, 214 stars), Software Design Review (atilladeniz/Kubeli, 387 stars), Nv Endpoint Routed Tool Provider (novuhq/novu, 40k stars) and Rollback Changes (maslennikov-ig/claude-code-orchestrator-kit, 260 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Omh Refactor Plan?

rlaope (a GitHub user) maintains it in rlaope/oh-my-hermes, which has 3,233 GitHub stars. The repository holds 143 skills in this directory. The repository was last updated on October 8, 2026.

Source: rlaope/oh-my-hermes on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.