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.
npx skills add xdg/xdg-claude --skill how-to-refactorgit clone --depth 1 https://github.com/xdg/xdg-claudeWrote 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.
[](https://agentmods.dev/skills/xdg/xdg-claude/how-to-refactor)<a href="https://agentmods.dev/skills/xdg/xdg-claude/how-to-refactor"><img src="https://agentmods.dev/badge/skills/xdg/xdg-claude/how-to-refactor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xdg/xdg-claude/how-to-refactor"><img src="https://agentmods.dev/badge/skills/xdg/xdg-claude/how-to-refactor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.00638 |
| Opus 5.5 | $0.00020 | $0.00255 |
| Sonnet 5.5 | $0.00010 | $0.00128 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
how-to-refactor 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handling refactoring requests
Delegate to the refactor subagent (Agent tool, subagent_type: refactor) when the user wants code restructured without behavior change. The subagent executes one atomic refactoring, runs tests to verify behavior preservation, and stops. Doing this work in the main session risks tangling refactor edits with unrelated changes and consumes context on diff-level reasoning.
For broader "what should I refactor?" questions, use plan-refactor instead -- see how-to-plan-refactor.
When to delegate vs. handle inline
Delegate when:
- The user names a specific refactoring: "extract this function", "rename X to Y everywhere", "remove duplication in module Z", "simplify the conditionals in fn()".
- The user picks an item from a
plan-refactorreport and asks you to carry it out. - The change is mechanical but spans enough code that tests must verify behavior preservation.
Handle inline (do not delegate) when:
- The user is deciding whether to refactor -- that is conversation, not execution.
- The refactor is a one-line rename inside code already loaded in conversation. Subagent overhead exceeds the work.
- The request mixes refactoring with feature changes or bug fixes. The subagent refuses combined changes -- split first.
Crafting the delegation prompt
The subagent requires a specific target. Pass exact instructions: what to refactor, what technique to apply (if known), what scope (one site vs. all instances).
Examples:
- User: "extract lines 45-60 of auth.go into a function" → "Extract lines 45-60 of auth.go into a well-named function."
- User: "rename getUserData to fetchUserData" → "Rename
getUserDatatofetchUserDataacross the codebase. Verify tests pass." - User: "simplify the conditionals in validateUser()" → "Simplify the conditionals in validateUser(). Preserve all observable behavior including error handling."
- User: "dedupe the email validation in user-service.ts" → "Eliminate the duplicate email validation logic in user-service.ts. Extract a shared function."
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.
- 1mo ago Changed ab379f4f4638
- 2mo ago First seen · 42 lines · 50 tokens per session scan A 9866274a2c85
how-to-refactor is a skill published in the GitHub repository xdg/xdg-claude (20 stars, last pushed 6d ago), licensed Apache-2.0. It adds 50 tokens to every session and 638 once invoked, about $0.0002 per session on Opus 5.5. 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.
how-to-refactor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| how-to-refactorxdg/xdg-claude | Skill | 20 | 6d ago | Apache-2.0 | A | 50 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |