codehub-refactoring

Refactoring analysis for planning code changes such as renaming, extracting, splitting, or moving code. It maps references and dependencies but does not edit the source files.

In plain words
What is it for?
Use it to find callers and dependents, trace incoming and outgoing references, check data-shape changes, and verify a completed refactor.
Why use it?
It shows what may be affected before a refactor and checks afterward whether the changes stayed within the expected scope.

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/theagenticguy/opencodehub/codehub-refactoring
Any agent
npx skills add theagenticguy/opencodehub --skill codehub-refactoring
Clone the repo
git clone --depth 1 https://github.com/theagenticguy/opencodehub

Made for: Claude Code, Codex.

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,206 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 $0.00089 $0.02206
Opus 5 $0.00044 $0.01103
Sonnet 5 $0.00018 $0.00441
Haiku 4.5 $0.00009 $0.00221

Measured yesterday against content hash 085653b4a38a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codehub-refactoring 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 yesterday.

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.

plugins/opencodehub/skills/codehub-refactoring/SKILL.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactoring support with OpenCodeHub

OpenCodeHub's MCP surface is read-only with respect to your source — no tool edits the working tree. This skill uses the graph to plan a refactor (map the blast radius and every reference before you touch anything) and to verify it afterward (confirm the diff matches the plan and nothing unexpected moved). The actual edits are made by you or your editor; OpenCodeHub tells you exactly what to change and then checks your work.

When to Use

  • "What will break if I rename validateUser?"
  • "Map every caller before I extract this into a module."
  • "Where are all the references to this symbol — including dynamic ones?"
  • "I just refactored — did the change touch only what I expected?"
  • Any rename, extract, split, or move where you need the dependency picture before editing and a verification pass after.

Workflow

PLAN
1. mcp__codehub__impact({ name: target, direction: "upstream" })   → All dependents (the edit list)
2. mcp__codehub__context({ name: target })                         → Incoming / outgoing refs + processes
3. mcp__codehub__shape_check (if the symbol is a route/payload)    → Producer/consumer drift to watch
4. Build the edit plan from impact's d=1 set + context's refs

APPLY (you / your editor — OpenCodeHub does not do this)
5. Make the edits in your editor or with the language server's rename

VERIFY
6. mcp__codehub__detect_changes({ scope: "unstaged" })             → What the diff actually touched
7. Cross-check changed_symbols against the plan — any surprise is a miss
8. Run tests for the affected processes

If the context envelope warns the index is stale, run codehub analyze first — a stale graph produces an incomplete plan and a misleading verification.

Checklists

Plan and verify a symbol rename

PLAN
- [ ] mcp__codehub__impact({ name, direction: "upstream" }) — enumerate every dependent; this is your edit list
- [ ] mcp__codehub__context({ name }) — see inbound + outbound refs, including ACCESSES edges
      (pass `file_path` and/or `kind` to disambiguate when the name is ambiguous)
- [ ] Note the confidenceBreakdown: `unknown > 0` means a heuristic edge the SCIP
      oracle contradicted — inspect those by reading source before trusting them
- [ ] Watch for dynamic references the graph cannot see (string-keyed dispatch,
      reflection, config JSON, doc comments) — list them as manual-check items

APPLY (your editor / LSP rename — not an OpenCodeHub tool)
- [ ] Apply the rename across the files impact + context named

VERIFY
- [ ] mcp__codehub__detect_changes({ scope: "unstaged" }) — confirm the diff scope
- [ ] Cross-check detect_changes against impact's d=1 count — a gap means a missed reference
- [ ] Run tests for every affected process

Read the full file on GitHub · 211 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. yesterday First seen · 211 lines · 89 tokens per session scan A 085653b4a38a

Subscribe to this mod's changes

codehub-refactoring is a skill published in the GitHub repository theagenticguy/opencodehub (3 stars, last pushed 20d ago), licensed Apache-2.0. It adds 89 tokens to every session and 2,206 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 2026-08-31.

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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens