refactor

A code-cleanup command that reorganizes a selected file, function, pattern, or set of changes according to coding best practices.

In plain words
What is it for?
Use it to improve code quality in a named file or function, or to refactor unstaged or recently changed files.
Why use it?
It helps make code easier to maintain and can target either a specific area or your current changes.

Command

Install

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.

agentmods
npx agentmods add commands/rileyhilliard/agentrc/refactor
Clone the repo
git clone --depth 1 https://github.com/rileyhilliard/agentrc
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 267 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00006 $0.00267
Opus 5 $0.00003 $0.00133
Sonnet 5 $0.00001 $0.00053
Haiku 4.5 $0.00001 $0.00027

Measured yesterday against content hash 0cf11a70e849, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

.agentrc/commands/refactor.md · 30 lines

What it actually says

Refactor code to improve quality, maintainability, and adherence to best practices.

Arguments:

  • $ARGUMENTS: File path, function name, or pattern to refactor. If not provided, refactors unstaged changes.

First, determine what code to refactor:

If $ARGUMENTS is provided:

  • Use the provided file path, pattern, or user instructions directly

If $ARGUMENTS is empty:

  • If there are unstaged changes, use those as the refactoring target
  • If no unstaged changes, use the following command to detect the set of changed files: git diff --name-only $([ "$(git rev-parse --abbrev-ref HEAD)" = "main" ] && echo "HEAD^" || echo "main...HEAD")

Once you have the target, invoke the ce:refactoring-code skill using the Skills tool with:

  • A detailed prompt that includes:
    • What code to refactor (file paths, function names, or the diff of unstaged changes)
    • Any specific focus areas mentioned by the user
    • Instructions to follow the refactoring guidelines in the agent's prompt
Changes

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.

  1. yesterday First seen · 30 lines · 6 tokens per session scan A 0cf11a70e849

Subscribe to this mod's changes

refactor is a command published in the GitHub repository rileyhilliard/agentrc (3 stars, last pushed 6mo ago), licensed MIT. It adds 6 tokens to every session and 267 once invoked, about $0.0000 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 2026-08-31.