refactor

A command that reviews and changes code to make it clearer, smaller, or more consistent. Refactoring means improving code structure without changing what the program is meant to do.

In plain words
What is it for?
Extracting functions, splitting modules, renaming symbols, cleaning up code smells, planning changes without applying them, and applying changes with selected safety settings.
Why use it?
It helps address long functions, oversized modules, repeated patterns, unclear names, and other code-structure problems.

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/alphaaiservice/cortex/refactor
Clone the repo
git clone --depth 1 https://github.com/alphaaiservice/cortex
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,914 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 $0.00050 $0.07914
Opus 5 $0.00025 $0.03957
Sonnet 5 $0.00010 $0.01583
Haiku 4.5 $0.00005 $0.00791

Measured yesterday against content hash 613821f21b87, 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.

commands/refactor.md · 841 lines

How it starts

The opening of the file, as written. The whole thing — 841 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI-Powered Code Refactoring

Refactor target: $ARGUMENTS

Parse $ARGUMENTS to extract:

  • target: file path or directory path (required)
  • --type: refactoring focus — extract, decompose, rename, cleanup, or all (default: all)
  • --yes: skip confirmation prompt and apply all recommended refactorings automatically
  • --dry-run: analyze and plan only, do not apply any changes
  • --aggressive: lower thresholds (functions >30 lines, files >300 lines, nesting >3)
  • --conservative: raise thresholds (functions >80 lines, files >800 lines, nesting >5)

If no target is provided, default to the current working directory.


Step 0: Safety — Worktree Isolation (MANDATORY before any mutation)

📖 CANONICAL REFERENCE: commands/references/WORKTREE_SAFETY.md defines the safety decision tree for all file-mutation commands. Load it and follow it BEFORE any Write / Edit / Bash mutation in this run.

Quick summary (full tree + rationale in the reference file):

  1. Confirm scope with the user, then ask: isolated worktree (DEFAULT, recommended) vs current checkout (risky, requires opt-in) vs cancel.
  2. Isolated worktree (default): either spawn the mutation phase as Agent({ ..., isolation: "worktree" }), OR manually git worktree add ../<repo>-refactor-$(date +%s) -b refactor/auto. After completion, show the diff and let the user merge / cherry-pick / discard.
  3. Current checkout (only with explicit user opt-in): refuse if git status --porcelain is non-empty; create a savepoint commit before any mutation so rollback is git reset --hard HEAD~1.
  4. No git: refuse to proceed.

Never start mutating files before completing this decision tree.


Step 0.5: Pre-Flight Validation

Before doing anything, validate the environment:

# Verify target exists
ls -la $TARGET 2>/dev/null || echo "ERROR: Target not found"

# Detect project language(s)
# Python: look for .py files, pyproject.toml, requirements.txt
# TypeScript: look for .ts/.tsx files, tsconfig.json, package.json
# JavaScript: look for .js/.jsx files, package.json
# Go: look for .go files, go.mod
# Rust: look for .rs files, Cargo.toml

# Check for git — we need it for safe rollback
git status 2>/dev/null || echo "WARNING: Not a git repo — no rollback safety net"

# Stash any uncommitted changes if present (safety)
git stash list 2>/dev/null

Read the full file on GitHub · 841 lines

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 · 841 lines · 50 tokens per session scan A 613821f21b87

Subscribe to this mod's changes

refactor is a command published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 26d ago), licensed MIT. It adds 50 tokens to every session and 7,914 once invoked, about $0.0003 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.