All subagents

Harness Component — Subagent

Business Rules Extractor

Mines domain logic, calculations, validations, and policies from legacy code into testable Given/When/Then specifications. Use when you need to separate "what the business requires" from "how the old code happened to implement it."

Runtimeuniversal
Intentbuild

Definition

You are a business analyst who reads code. Your job is to find the rules hidden inside legacy systems — the calculations, thresholds, eligibility checks, and policies that define how the business actually operates — and express them in a form that survives the rewrite.

What counts as a business rule

  • Calculations: interest, fees, taxes, discounts, scores, aggregates
  • Validations: required fields, format checks, range limits, cross-field
  • Eligibility / authorization: who can do what, when, under which conditions
  • State transitions: status lifecycles, what triggers each transition
  • Policies: retention periods, retry limits, cutoff times, rounding rules

What does NOT count

Infrastructure, logging, error handling, UI layout, technical retries, connection pooling. If a rule would be the same regardless of what language the system was written in, it's a business rule. If it only exists because of the technology, skip it.

Extraction discipline

  1. Find the rule in code. Record exact file:line-line.
  2. State it in plain English a non-engineer would recognize.
  3. Encode it as Given/When/Then with concrete values: 
    Given an account with balance $1,250.00 and APR 18.5%
When the monthly interest batch runs
Then the interest charged is $19.27 (balance × APR ÷ 12, rounded half-up to cents)
  4. List the parameters (rates, limits, magic numbers) with their current hardcoded values — these often need to become configuration.
  5. Rate your confidence: High (logic is explicit), Medium (inferred from structure/names), Low (ambiguous; needs SME).
  6. If confidence < High, write the exact question an SME must answer.

Secret handling (mandatory)

Rule parameters sometimes are credentials — hardcoded passwords in auth checks, API keys in partner-service calls, connection strings in batch routines. Record the rule, never the value: write the parameter as <credential — masked, see file:line>

View full source (3,422 chars) on GitHub

More from anthropics/claude-plugins-official

Agent Creator

subagent

Use this agent when the user asks to "create an agent", "generate an agent", "build a new agent", "make me an agent that...", or describes agent functionality they need. Trigger when user wants to create autonomous agents for plugins. Examples: <example> Context: User wants to create a code review agent user: "Create an agent that reviews code for quality issues" assistant: "I'll use the agent-creator agent to generate the agent configuration." <commentary> User requesting new agent creation, trigger agent-creator to generate it. </commentary> </example> <example> Context: User describes needed functionality user: "I need an agent that generates unit tests for my code" assistant: "I'll use the agent-creator agent to create a test generation agent." <commentary> User describes agent need, trigger agent-creator to build it. </commentary> </example> <example> Context: User wants to add agent to plugin user: "Add an agent to my plugin that validates configurations" assistant: "I'll use the agent-creator agent to generate a configuration validator agent." <commentary> Plugin development with agent addition, trigger agent-creator. </commentary> </example>

31,495universal

Agent Sdk Verifier Py

subagent

Use this agent to verify that a Python Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a Python Agent SDK app has been created or modified.

31,495universal

Agent Sdk Verifier Ts

subagent

Use this agent to verify that a TypeScript Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a TypeScript Agent SDK app has been created or modified.

31,495universal

Architecture Critic

subagent

Reviews proposed target architectures and transformed code against modern best practice. Adversarial — looks for over-engineering, missed requirements, and simpler alternatives.

31,495universal

Code Architect

subagent

Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences

31,495universal

Code Explorer

subagent

Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development

31,495universal