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/bienhoang/refactoring-kitWrote 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/bienhoang/refactoring-kit/refactor)<a href="https://agentmods.dev/commands/bienhoang/refactoring-kit/refactor"><img src="https://agentmods.dev/badge/commands/bienhoang/refactoring-kit/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/bienhoang/refactoring-kit/refactor"><img src="https://agentmods.dev/badge/commands/bienhoang/refactoring-kit/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 | $0.00017 | $0.00697 |
| Opus 5.5 | $0.00007 | $0.00279 |
| Sonnet 5.5 | $0.00003 | $0.00139 |
| Haiku 4.5 | $0.00002 | $0.00070 |
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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze target and route to the best refactoring command: $ARGUMENTS
Decision Tree
0. Empty arguments:
- If
$ARGUMENTSis empty → UseAskUserQuestion:- "What would you like to refactor? Provide a file path, directory, or description."
1. Check for review intent:
- If
$ARGUMENTScontains action keywords: "review", "analyze", "audit", "scan", "assess", "inspect", "report" as standalone words (not inside file paths) - Or if
$ARGUMENTSstarts with--review→/refactor:review <target>(strip the keyword, pass remaining as target) - Note: If target is a
.mdplan file AND contains a review keyword (e.g., "review my plan.md"), prefer plan routing (Step 2) — the user likely wants to execute the plan, not review it
1.5. Check for architecture intent:
- If
$ARGUMENTScontains architecture keywords: "architecture", "architectural", "arch-review", "style detection", "boundary analysis", "layer violations" as standalone words (not inside file paths) - Or if
$ARGUMENTSstarts with--architectureor--arch→/refactor:architecture <target>(strip the keyword, pass remaining as target)
2. Check for existing plan:
- If
$ARGUMENTSis a path to a.mdplan file →/refactor:implement <path> - If active refactoring plan exists in
./plans/matching "refactor" →/refactor:implement
3. Route by scope:
A) Single File (target is a file path like src/utils.ts, lib/helpers.js)
→ /refactor:fast <target>
B) Small Scope (target mentions specific function, class, or method)
→ /refactor:fast <target>
C) Multi-file list or glob patterns (e.g., src/*.ts, file1.js file2.js)
→ /refactor:plan <target>
D) Directory / Module (target is a directory like src/services/, lib/)
→ /refactor:plan <target>
E) Large Scope (keywords: system, module, large, entire, whole, codebase)
→ /refactor:plan <target>
F) Ambiguous (cannot determine scope from arguments)
→ Use AskUserQuestion with options:
- "/refactor:review — Read-only analysis report"
- "/refactor:architecture — Architectural style & smell analysis"
- "/refactor:fast — Quick autonomous refactoring"
- "/refactor:plan — Brainstorm & plan first"
- "/refactor:implement — Execute with review-then-apply"
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 · 59 lines · 17 tokens per session scan A 78d1da30ba9b
refactor is a command published in the GitHub repository bienhoang/refactoring-kit (4 stars, last pushed 8mo ago), licensed MIT. It adds 17 tokens to every session and 697 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
refactor
Systematic code refactoring with smart scope detection.
init
Install the formatters this repository needs, with every command visible before it runs.
spec-trace-requirements
You are verifying that implementation changes trace back to specification requirements.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).