fix

A command that finds code-standards problems and proposes small, cautious code changes to fix them. It shows the plan and asks for confirmation before each change.

In plain words
What is it for?
Use it to review a directory or selected code, plan refactoring, split large files, extract functions, simplify complex code, and separate mixed responsibilities.
Why use it?
It helps remove issues such as oversized files, oversized functions, complicated code, and files handling too many responsibilities without making unapproved edits.

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/hculap/better-code/fix
Clone the repo
git clone --depth 1 https://github.com/hculap/better-code
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,140 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 $0.00013 $0.01140
Opus 5 $0.00006 $0.00570
Sonnet 5 $0.00003 $0.00228
Haiku 4.5 $0.00001 $0.00114

Measured yesterday against content hash 7816ebf4866b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fix 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.

plugins/code-standards/commands/fix.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Standards Fix

Auto-refactor $ARGUMENTS to fix code standards violations. Uses conservative mode - shows plan first, asks for confirmation before each change.

If no argument provided, analyze and offer to fix violations in the current directory.

Fix Process

Step 1: Analyze Violations

First, perform the same analysis as /code-standards:check to identify all violations.

Categorize violations by type:

  • File too large - needs splitting
  • Function too large - needs extraction
  • High complexity - needs simplification
  • Mixed responsibilities - needs separation

Step 2: Generate Fix Plan

For each violation, propose a specific fix:

## Fix Plan

Found 4 violations in $ARGUMENTS. Here's the proposed fix plan:

### 1. Split `src/services/order.ts` (912 LOC → ~300 LOC each)

**Current:** Single file handling all order logic
**Proposed:** Split into 3 files:
- `src/services/order-creation.ts` - createOrder, validateOrder
- `src/services/order-processing.ts` - processOrder, handlePayment
- `src/services/order-fulfillment.ts` - shipOrder, trackOrder

**Impact:**
- Creates 3 new files
- Updates imports in 5 dependent files
- Original file will be deleted

### 2. Extract from `processPayment` (complexity 22 → ~8 each)

**Current:** Large switch statement for payment methods
**Proposed:** Strategy pattern with separate handlers:
- `PaymentProcessor` interface
- `CreditCardProcessor`, `PayPalProcessor`, `BankTransferProcessor`

**Impact:**
- Creates 4 new classes
- Simplifies `processPayment` to dispatcher

### 3. Extract validation from `createUser` (78 LOC → ~25 LOC)

**Current:** Validation mixed with user creation
**Proposed:** Extract to `validateUserData()` function

**Impact:**
- Adds 1 new function
- Reduces `createUser` by ~50 LOC

### 4. Split `formatData` helper (62 LOC → ~20 LOC each)

**Current:** Handles multiple data types in one function
**Proposed:** Split by type:
- `formatUserData()`, `formatOrderData()`, `formatProductData()`

**Impact:**
- Adds 3 new functions
- Original function becomes dispatcher

---

**Total changes:** 3 file splits, 2 function extractions, 8 new functions/classes

Read the full file on GitHub · 159 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 · 159 lines · 13 tokens per session scan A 7816ebf4866b

Subscribe to this mod's changes

fix is a command published in the GitHub repository hculap/better-code (2 stars, last pushed 7mo ago), licensed MIT. It adds 13 tokens to every session and 1,140 once invoked, about $0.0001 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.