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.
git clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/commands/kensaurus/cursor-kenji/refactor)<a href="https://agentmods.dev/commands/kensaurus/cursor-kenji/refactor"><img src="https://agentmods.dev/badge/commands/kensaurus/cursor-kenji/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/commands/kensaurus/cursor-kenji/refactor"><img src="https://agentmods.dev/badge/commands/kensaurus/cursor-kenji/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 | $0.00021 | $0.00229 |
| Opus 5.5 | $0.00008 | $0.00092 |
| Sonnet 5.5 | $0.00004 | $0.00046 |
| Haiku 4.5 | $0.00002 | $0.00023 |
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 23d 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
/refactor
Systematic refactoring: analyze → split → extract → verify behavior. Move code, do not retype it: edit surgically, keep every public API and behavior identical, and leave code the refactor does not touch untouched. A bug you find on the way is a follow-up, not part of the refactor.
This command is a thin entry point. The full playbook lives in the workflow-refactor skill, which covers safe incremental transformations, splitting large files, extracting components/hooks, and dependency-aware verification.
Use /refactor when you want to explicitly trigger refactoring. Otherwise, say "refactor this", "split this file", "extract a hook", or "clean up this module" and the skill auto-fires.
Related: audit-code-quality for spotting smells before refactoring, audit-code-review for verifying behavior preservation after.
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.
- 23d ago Changed · +1 lines cd9f870b3c43
- 1mo ago First seen · 15 lines · 21 tokens per session scan A 238cf5aacbc8
refactor is a command published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 18d ago), licensed MIT. It adds 21 tokens to every session and 229 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 commands, from other repositories
code-review
Confidence-based code review checklist.
execute
Run task execution workflow step-by-step.
mcp
Switch MCP mode to optimize context window.
prp-review
Review and validate an existing PRP.
commit
Git commit with conventional commits format.
checklist
Generate a custom checklist for the current feature based on user requirements.