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 usrrname/cursorrules --skill refactor-agentgit clone --depth 1 https://github.com/usrrname/cursorrulesWrote 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/usrrname/cursorrules/refactor-agent)<a href="https://agentmods.dev/skills/usrrname/cursorrules/refactor-agent"><img src="https://agentmods.dev/badge/skills/usrrname/cursorrules/refactor-agent/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/usrrname/cursorrules/refactor-agent"><img src="https://agentmods.dev/badge/skills/usrrname/cursorrules/refactor-agent.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 | $0.00028 | $0.01041 |
| Opus 5.5 | $0.00011 | $0.00416 |
| Sonnet 5.5 | $0.00006 | $0.00208 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
refactor-agent 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.
What it actually says
Critical Rules
- Always detect and state the programming language of the code block before refactoring
- Refactor when the user request includes terms like "refactor", "improve", "optimize", "clean up", or similar
- Always preserve the original intent and functionality unless the user requests a change
- If code contains duplication, refactor first, and test, before introducing a change.
- Use idiomatic, modern, and maintainable patterns for the detected language
- Add or update comments and documentation as appropriate
- If the code or modification request is ambiguous, ask clarifying questions before proceeding
- Provide before/after code examples in the response
- If the code block is part of a larger file, ensure changes do not break unrelated code
- Run or suggest updates to relevant tests after refactoring
- Make as few changes as possible while preserving readability to limit the amount of errors that may arise from potentially destroying existing functionality the user intended to preserve.
- If it exists, identify contradictory requirements and existing implementation in other areas of codebase that may prevent the refactor from succeeding.
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 First seen · 92 lines · 28 tokens per session scan A 975a212e4bf5
refactor-agent is a skill published in the GitHub repository usrrname/cursorrules (11 stars, last pushed 6mo ago), licensed ISC. It adds 28 tokens to every session and 1,041 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
analyze
Deep codebase analysis — complexity, coupling, dead code, tech debt hotspots.
explore
Read-only codebase exploration — understand structure, data flow, and conventions before changing anything.
incident
Production incident response — structured triage, hypothesis tree, safe remediation, incident record.
review
Code review checklist — catch bugs, security issues, and design problems before merging.
autopilot
Fully autonomous execution — clarify, plan, and execute without interruption.
chaos
Failure injection — stress test implementations under hostile conditions before shipping.