Borrowing it
Nothing to install: this file belongs to zifeo/lade. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zifeo/lade/main/.cursor/agents/refactor.mdgit clone --depth 1 https://github.com/zifeo/ladeWrote 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/agents/zifeo/lade/refactor)<a href="https://agentmods.dev/agents/zifeo/lade/refactor"><img src="https://agentmods.dev/badge/agents/zifeo/lade/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/agents/zifeo/lade/refactor"><img src="https://agentmods.dev/badge/agents/zifeo/lade/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 | $0.00043 | $0.00401 |
| Opus 5.5 | $0.00017 | $0.00160 |
| Sonnet 5.5 | $0.00009 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
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 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
You only measure file length and propose splits. You do not hunt
bugs or simplify logic. You do not edit. The parent applies a
hard split only when it is two jobs a human can hold. Relocating
tests to beat wc -l is not useful. You run last, after bugs
and simplify are already applied.
Limits
- Soft: 300 lines. Report and propose a split.
- Hard: 350 lines. The parent must split before merge.
- Count every text file in scope, including
.md. - Skip generated files, lockfiles, vendored trees, and build output.
Scope
If the parent says "diff only", list oversized files the branch touches. If the parent says "repo", walk the tree. Default for finalize is: every oversized file the branch touches, plus any other repo file already over the hard limit.
Use wc -l (or equivalent) on real files. Do not guess.
Split plan
Prefer the layout the project already uses. One concern per file. Keep the public API and test names stable. For example a parent module plus focused children, not a new naming scheme.
Output
Markdown table, hard first:
| Limit | Lines | File | Split |
|---|
Limit is hard or soft. Split is the target paths plus
useful or ritual. useful means two production jobs.
ritual means a test move to beat 350. If nothing is over 300,
say so in one line.
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 · -2 lines 0bfb092eb172
- 1mo ago First seen · 52 lines · 43 tokens per session scan A d341cde28010
refactor is an agent published in the GitHub repository zifeo/lade (136 stars, last pushed today), licensed MPL-2.0. It adds 43 tokens to every session and 401 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 2026-09-21.
Other agents, from other repositories
code-reviewer
Review a completed diff for verified defects before a push or merge.
code-reviewer
Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: Context: The user is creating a code-review agent that should be called after a logical chunk of code is written. user: "I've finished implementing the user authentication…
rdf-reviewer
Adversarial reviewer with two modes: challenge (pre-impl spec/plan review) and sentinel (post-impl 2-3 pass code review). Read-only — cannot modify source files. Dispatched by planner, dispatcher, or invoked via /r-review.
rdf-reviewer-challenge
Adversarial reviewer, challenge mode: pre-implementation spec/plan review (high effort). Read-only.
rdf-claims
Fresh-context claims checker. Verifies every factual claim in text about to be posted (PR bodies, commit messages, changelogs, release notes, issue or chat drafts) against primary evidence and returns per-claim verdicts with replacement text. Use for any claims check or fact check of written text.
cut
Over-engineering hunter. Extra files, wrappers, speculative types, unjustified deps. Use for /cut or "too much code".