Parallel Agent Type Contracts

Parallel Agent Orchestration

AI-powered web search, research, and reasoning via Perplexity

Unit-aware computation with Pint - convert units, dimensional analysis, unit arithmetic

Planning agent that creates implementation plans and handoffs from conversation context

Identify failure modes before they occur using structured risk analysis

Formal theorem proving with research, testing, and verification phases

Code quality checks, formatting, and metrics via qlty CLI

QLTY During Development

Search past reasoning for relevant decisions and approaches

Query the memory system for relevant learnings from past sessions

Code refactoring workflow - analyze → plan → implement → review → validate

Check reference SDK implementations using btca ask

Release preparation workflow - security audit → E2E tests → review → changelog → docs

Store a learning, pattern, or decision in the memory system for future recall

Analyze repository structure, patterns, conventions, and documentation for understanding a new codebase

Use RepoPrompt CLI for token-efficient codebase exploration

Research agent for external documentation, best practices, and library APIs via MCP tools

External research workflow for docs, web, APIs - NOT codebase exploration

Document codebase as-is with thoughts directory for historical context

Resume work from handoff document with context analysis and validation

Comprehensive code review workflow - parallel specialized reviews → synthesis

Router-First Architecture

Search Tool Hierarchy

Choose the right search tool for each query type

Search Tool Hierarchy

Security audit workflow - vulnerability scan → verification

Computational geometry with Shapely - create geometries, boolean operations, measurements, predicates

Meta-skill for creating and managing Claude Code skills

Skill Development Rules

Upgrade any skill to v5 Hybrid format using decision theory + modal logic

Create and use Claude Code slash commands - quick prompts, bash execution, file references

Create and configure Claude Code sub-agents with custom prompts, tools, and models

Show users how Continuous Claude works - the opinionated setup with hooks, memory, and coordination

TDD workflow for migrations - orchestrate agents, zero main context growth

Orchestrator-only workflow for migrating/rewriting codebases with full TDD and agent delegation

Test-driven development workflow with philosophy guide - plan → write tests → implement → validate

Comprehensive testing workflow - unit tests ∥ integration tests → E2E tests

Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.

Full 5-layer analysis of a specific function. Use when debugging or deeply understanding code.

Get a token-efficient overview of any project using the TLDR stack

Maps questions to the optimal tldr command. Use this to pick the right layer

Show full session token usage, costs, TLDR savings, and hook activity

Friendly onboarding when users ask about capabilities

Validation agent that validates plan tech choices against current best practices

Wiring Verification

Goal-based workflow orchestration - routes tasks to specialist agents based on user goals

Evaluate acquisition channels using unit economics, customer quality, and scalability. Use when deciding whether to scale, test, or kill a growth channel.

Assess whether your product work is AI-first or AI-shaped. Use when evaluating AI maturity and choosing the next team capability to build.

Understand the PM-to-Director transition through altitude and horizon thinking. Use when diagnosing scope, time-horizon, or leadership-level gaps.