select-tool

A command that chooses between available MCP tools based on the operation's complexity and requirements. MCP tools are connected services that let the coding agent perform specialized work.

In plain words
What is it for?
Use it when selecting a tool for work involving different numbers of files, programming languages, frameworks, or semantic analysis needs.
Why use it?
It removes the need to decide manually which tool offers the best balance of speed and accuracy for an operation.

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/select-tool
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 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 764 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 $0.00015 $0.00764
Opus 5 $0.00008 $0.00382
Sonnet 5 $0.00003 $0.00153
Haiku 4.5 $0.00002 $0.00076

Measured 3d ago against content hash f97cf58381ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

select-tool 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/select-tool.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sc:select-tool - Intelligent MCP Tool Selection

Triggers

  • Operations requiring optimal MCP tool selection between Serena and Morphllm
  • Meta-system decisions needing complexity analysis and capability matching
  • Tool routing decisions requiring performance vs accuracy trade-offs
  • Operations benefiting from intelligent tool capability assessment

Usage

/sc:select-tool [operation] [--analyze] [--explain]

Behavioral Flow

  1. Parse: Analyze operation type, scope, file count, and complexity indicators
  2. Score: Apply multi-dimensional complexity scoring across various operation factors
  3. Match: Compare operation requirements against Serena and Morphllm capabilities
  4. Select: Choose optimal tool based on scoring matrix and performance requirements
  5. Validate: Verify selection accuracy and provide confidence metrics

Key behaviors:

  • Complexity scoring based on file count, operation type, language, and framework requirements
  • Performance assessment evaluating speed vs accuracy trade-offs for optimal selection
  • Decision logic matrix with direct mappings and threshold-based routing rules
  • Tool capability matching for Serena (semantic operations) vs Morphllm (pattern operations)

MCP Integration

  • Serena MCP: Optimal for semantic operations, LSP functionality, symbol navigation, and project context
  • Morphllm MCP: Optimal for pattern-based edits, bulk transformations, and speed-critical operations
  • Decision Matrix: Intelligent routing based on complexity scoring and operation characteristics

Tool Coordination

  • get_current_config: System configuration analysis for tool capability assessment
  • execute_sketched_edit: Operation testing and validation for selection accuracy
  • Read/Grep: Operation context analysis and complexity factor identification
  • Integration: Automatic selection logic used by refactor, edit, implement, and improve commands

Key Patterns

  • Direct Mapping: Symbol operations → Serena, Pattern edits → Morphllm, Memory operations → Serena
  • Complexity Thresholds: Score >0.6 → Serena, Score <0.4 → Morphllm, 0.4-0.6 → Feature-based
  • Performance Trade-offs: Speed requirements → Morphllm, Accuracy requirements → Serena
  • Fallback Strategy: Serena → Morphllm → Native tools degradation chain

Read the full file on GitHub · 88 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 · 88 lines · 15 tokens per session scan A f97cf58381ff

Subscribe to this mod's changes

select-tool is a command published in the GitHub repository SuperClaude-Org/SuperClaude_Framework (23,856 stars, last pushed 12d ago), licensed MIT. It adds 15 tokens to every session and 764 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.