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 agentmods add skills/tahirraufkeeyu/software-development-agent-stack--sdas/refactornpx skills add tahirraufkeeyu/software-development-agent-stack--sdas --skill refactorgit clone --depth 1 https://github.com/tahirraufkeeyu/software-development-agent-stack--sdasWrote 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/tahirraufkeeyu/software-development-agent-stack--sdas/refactor)<a href="https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/refactor"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/refactor.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.01732 |
| Opus 5 | $0.00026 | $0.00866 |
| Sonnet 5 | $0.00010 | $0.00346 |
| Haiku 4.5 | $0.00005 | $0.00173 |
Grade A, and why
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 5d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
- User says "refactor", "clean up", "extract a function", "rename", "split this class", "inline this helper".
- Code review found duplication, a god object, feature envy, or a long method and asked for a fix.
- Before adding a feature to code that is hard to change — refactor first, then add the feature.
Do not use this skill to change behaviour (that is a feature or bugfix). If a refactor reveals a bug, stop, note it, and address it as a separate change.
Inputs
- A target (file, function, class, or module) and the refactoring to perform. If the user gives a goal ("this function is too long"), pick the smallest refactoring that moves toward the goal.
- A passing test suite. If the target has no tests, generate characterisation tests first (invoke the
test-writerskill) and only then refactor.
Outputs
- A sequence of small commits (or a single commit with a clear step-by-step description if the repo does not want many commits). Each step is individually behaviour-preserving and leaves the test suite green.
- A summary listing each refactoring applied with its Fowler name and the file/line it was applied to.
Tool dependencies
- Read, Edit, Grep, Glob.
- The project's test runner; the project's formatter and linter.
- Optional: language-server-driven rename (
tsc --noEmit,pyright,gopls,rust-analyzer) via CLI to catch broken references.
Procedure
- Confirm the safety net. Run the test suite. If it is red, stop — refactoring on a red suite is unsafe. If coverage for the target is absent, invoke
test-writerto add characterisation tests. - Name the refactoring. Pick one from references/refactoring-patterns.md. If the intended change does not match a named refactoring, it is probably behaviour change in disguise — stop and clarify.
- Plan the smallest safe step. Large refactorings are sequences of small ones: extract variable, then extract method, then move method, rather than one big rewrite.
- Apply one step. Change only the files the step requires. Do not fix unrelated issues along the way.
- Run the formatter. Run the linter. Run the tests. If anything fails, revert the step and reconsider (the step was too big, or missed a call site).
- Commit the step with a message like
refactor: extract method sendWelcomeEmail from UserService.create(Conventional Commits, see thecommit-messageskill). - Repeat from step 3 until the goal is reached.
- Emit the summary listing the steps.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 175 lines · 51 tokens per session scan A 833ab6df6cbe
refactor is a skill published in the GitHub repository tahirraufkeeyu/software-development-agent-stack--sdas (18 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 1,732 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…