specialization

specialization is a command for Claude Code from ruvnet/sublinear-time-solver. It costs 0 tokens per session (340 once invoked), scanned A, a copy of specialization, MIT.

A way to train coding agents toward specific areas, such as JavaScript, Python, React, or testing. Agents learn from successful edits, reviews, fixes, and performance improvements.

In plain words
What is it for?
Use it to create specialist agents, build expertise for particular file or task types, and inspect their specializations.
Why use it?
It helps assign or develop agents with more focused experience instead of treating every coding task the same. Learnings can be shared across sessions.

Command for Claude Code

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/ruvnet/sublinear-time-solver/specialization
Clone the repo
git clone --depth 1 https://github.com/ruvnet/sublinear-time-solver

Made for: Claude Code.

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.

agentmods badge for specialization

README.md
[![agentmods](https://agentmods.dev/badge/commands/ruvnet/sublinear-time-solver/specialization.svg)](https://agentmods.dev/commands/ruvnet/sublinear-time-solver/specialization)
Your own site
<a href="https://agentmods.dev/commands/ruvnet/sublinear-time-solver/specialization"><img src="https://agentmods.dev/badge/commands/ruvnet/sublinear-time-solver/specialization.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 340 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 95% copy Near-identical to another mod 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 $0.00000 $0.00340
Opus 5 $0.00000 $0.00170
Sonnet 5 $0.00000 $0.00068
Haiku 4.5 $0.00000 $0.00034

Measured yesterday against content hash 502863bd2a4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specialization 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.

Origin

This is a copy

95% identical to specialization — 18 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/training/specialization.md · 63 lines

What it actually says

Agent Specialization Training

Purpose

Train agents to become experts in specific domains for better performance.

Specialization Areas

1. By File Type

Agents automatically specialize based on file extensions:

  • .js/.ts: Modern JavaScript patterns
  • .py: Pythonic idioms
  • .go: Go best practices
  • .rs: Rust safety patterns

2. By Task Type

Tool: mcp__claude-flow__agent_spawn
Parameters: {
  "type": "coder",
  "capabilities": ["react", "typescript", "testing"],
  "name": "React Specialist"
}

3. Training Process

The system trains through:

  • Successful edit operations
  • Code review patterns
  • Error fix approaches
  • Performance optimizations

4. Specialization Benefits

# Check agent specializations
Tool: mcp__claude-flow__agent_list
Parameters: {"swarmId": "current"}

Result shows expertise levels:
{
  "agents": [
    {
      "id": "coder-123",
      "specializations": {
        "javascript": 0.95,
        "react": 0.88,
        "testing": 0.82
      }
    }
  ]
}

Continuous Improvement

Agents share learnings across sessions for cumulative expertise!

CLI Usage

# Train agent specialization via CLI
npx claude-flow train agent --type coder --capabilities "react,typescript"

# Check specializations
npx claude-flow agent list --specializations
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 · 63 lines · 0 tokens per session scan A 502863bd2a4a

Subscribe to this mod's changes

specialization is a command published in the GitHub repository ruvnet/sublinear-time-solver (89 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 340 tokens. A static security scan graded it A with 0 findings. It is 95% identical to specialization, differing in 18 lines, and is treated as a copy.