sc:recommend

A command that recommends which SuperClaude command best fits a user's request. It analyzes the request and recognizes common terms in English and Turkish.

In plain words
What is it for?
Use it to get command suggestions for tasks such as building a website, investigating an error, analyzing a problem, or improving performance.
Why use it?
It helps users choose the right command when they are unsure which available feature matches their goal.

Command

Part of the superclaude plugin — 2 skills, 30 commands, 20 agents, 1 hook, 2 MCP servers shipped together

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/superclaude-org/superclaude_framework/recommend
Clone the repo
git clone --depth 1 https://github.com/SuperClaude-Org/SuperClaude_Framework

Or install superclaude, the plugin that ships this one along with the rest of its 2 skills, 30 commands, 20 agents, 1 hook, 2 MCP servers.

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,194 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 $0.00022 $0.08194
Opus 5 $0.00011 $0.04097
Sonnet 5 $0.00004 $0.01639
Haiku 4.5 $0.00002 $0.00819

Measured 3d ago against content hash bd00fffbe126, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sc:recommend 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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

plugins/superclaude/commands/recommend.md · 1,006 lines

How it starts

The opening of the file, as written. The whole thing — 1,006 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SuperClaude Intelligent Command Recommender

Purpose: Ultra-intelligent command recommendation engine - recommends the most suitable SuperClaude commands for any user input

Command Definition

/sc:recommend [user request] --options [flags]

Multi-language Support

Language Detection and Translation System

language_mapping:
  turkish_keywords:
    machine_learning: ["machine learning", "ml", "artificial intelligence", "ai"]
    website: ["website", "web site", "site", "page"]
    application: ["app", "application", "program", "software"]
    error: ["error", "bug", "issue", "problem"]
    performance: ["performance", "speed", "fast", "optimization"]
    new: ["new", "create", "build", "start", "develop"]
    analysis: ["analyze", "analysis", "examine", "research"]

  english_keywords:
    machine learning: ["machine learning", "artificial intelligence", "ml", "ai"]
    website: ["website", "site", "page", "web application"]
    performance: ["performance", "speed", "optimization", "speed"]
    error: ["error", "issue", "bug", "problem"]

  universal_patterns:
    question_words: ["how", "what", "why", "which"]
    action_words: ["do", "create", "build", "develop"]
    help_words: ["help", "suggest", "recommend", "learn"]

Language Detection Algorithm

def detect_language_and_translate(input_text):
    turkish_chars = ['ç', 'ğ', 'ı', 'ö', 'ş', 'ü']
    if any(char in input_text.lower() for char in turkish_chars):
        return "tr"

    english_common = ["the", "and", "is", "are", "was", "were", "will", "would", "could", "should"]
    if any(word in input_text.lower().split() for word in english_common):
        return "en"

    return "en"  # Default to English

Multi-language Examples

# Turkish examples
/sc:recommend "makine öğrenmesi algoritması başlat"
/sc:recommend "sitem yavaş açılıyor, ne yapayım?"
/sc:recommend "yeni bir özellik eklemeliyim"
/sc:recommend "hata alıyorum, çözüm bul"

# English examples
/sc:recommend "I want to build ML algorithm"
/sc:recommend "my website is slow, help me optimize"
/sc:recommend "I need to add a new feature"
/sc:recommend "getting errors, need debugging"

# Mixed language
/sc:recommend "makine learning projesi yapmak istiyorum"

Read the full file on GitHub · 1,006 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. 3d ago First seen · 1,006 lines · 22 tokens per session scan A bd00fffbe126

Subscribe to this mod's changes

sc:recommend is a command published in the GitHub repository SuperClaude-Org/SuperClaude_Framework (23,856 stars, last pushed 13d ago), licensed MIT. It adds 22 tokens to every session and 8,194 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 2026-08-30.