A command that studies an Optimizely CMS codebase and creates skills describing the project's own coding patterns. The generated skills are instruction files that teach an agent how the project is structured and built.

Use it to generate, update, preview, or force-regenerate project skills, optionally including sanitized code examples and choosing a custom output directory.

It reduces the effort of explaining project-specific content types, services, architecture, and conventions to an agent by extracting them from the codebase.

enhance — Command for Claude Code by smithdak

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.

Clone the repo

git clone --depth 1 https://github.com/smithdak/claude-marketplace

Made for: Claude Code.

Or install optimizely, the plugin that ships this one along with the rest of its 5 skills, 4 commands, 10 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/smithdak/claude-marketplace/enhance/github.svg)](https://agentmods.dev/commands/smithdak/claude-marketplace/enhance)

Your own site

<a href="https://agentmods.dev/commands/smithdak/claude-marketplace/enhance"><img src="https://agentmods.dev/badge/commands/smithdak/claude-marketplace/enhance/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/smithdak/claude-marketplace/enhance"><img src="https://agentmods.dev/badge/commands/smithdak/claude-marketplace/enhance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,139 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00016	$0.01139
Opus 5	$0.00008	$0.00570
Sonnet 5	$0.00003	$0.00228
Haiku 4.5	$0.00002	$0.00114

Measured 9d ago against content hash ac91717fafb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

enhance 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 9d 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.

plugins/optimizely-cms-analyzer/commands/enhance.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Optimizely Enhance Command

Generate project-specific AI skills by extracting patterns from your Optimizely CMS codebase.

Usage

/optimizely:enhance                    # Generate skills to .claude/skills/
/optimizely:enhance --output ./skills  # Custom output path
/optimizely:enhance --update           # Update existing skills
/optimizely:enhance --force            # Force regeneration

Options

Option	Description
`--output <path>`	Output directory (default: `.claude/skills/`)
`--dry-run`	Preview what would be generated without writing files
`--include-examples`	Extract sanitized code examples from codebase
`--update`	Update existing skills instead of regenerating (compares with `.meta.json`)
`--force`	Overwrite existing skills without confirmation

What It Does

The enhance command analyzes your codebase to:

Extract Patterns - Identify conventions and patterns used in your project
Learn Structure - Understand content types, services, and architecture
Generate Skills - Create SKILL.md files that teach Claude your patterns

Generated Skills

Content Types Skill

Teaches Claude your content type patterns:

Base class hierarchy
Property conventions
GUID and attribute patterns
Content area restrictions

Services Skill

Teaches Claude your service layer:

Interface patterns
Dependency injection
Async conventions
Error handling

Controllers Skill

Teaches Claude your controller patterns:

Page/Block controller patterns
ViewModel construction
Action conventions

Project Conventions Skill

Consolidates project-wide conventions:

Naming standards
File organization
Configuration patterns

Testing Patterns Skill

Teaches Claude your testing patterns:

Test framework and mocking library
Content mocking strategies
Service and controller test patterns
Integration test fixtures

Error Handling Skill

Teaches Claude your error handling:

Logging framework and patterns
Custom exception hierarchy
API error responses (ProblemDetails)
Resilience patterns (Polly)

Read the full file on GitHub · 176 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.

9d ago First seen · 176 lines · 16 tokens per session scan A ac91717fafb7

Subscribe to this mod's changes

enhance is a command published in the GitHub repository smithdak/claude-marketplace (3 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 1,139 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.

Building agents

enhance