parcadei

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

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

Migration and upgrade review

General bug investigation and root cause analysis

Analyze brownfield codebase and create initial continuity ledger

Fast codebase search via WarpGrep (20x faster than grep)

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

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

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

Research-to-implement pipeline chaining 5 MCP tools with graceful degradation

Session analysis, precedent lookup, and learning extraction

Guide to the math cognitive stack - what tools exist and when to use each

Choose the right search tool for each query type

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

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

Multi-agent coordination for complex patterns

Migration workflow - research → analyze → plan → implement → review

Analyze Claude Code sessions using Braintrust logs

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

System health check (MOT) for skills, agents, hooks, and memory

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

Performance profiling, race conditions, memory issues

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

Lightweight fixes and quick tweaks

Code quality checks, formatting, and metrics via qlty CLI

Search past reasoning for relevant decisions and approaches

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

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

Codebase exploration and pattern finding

Formal theorem proving with research, testing, and verification phases

Refactoring planning AND migration planning

Planning agent that creates implementation plans and handoffs from conversation context

Resume work from handoff document with context analysis and validation

Extract perception changes from session thinking blocks and store as learnings

External research - web, docs, APIs with optional LLM

Fast file editing via Morph Apply API (10,500 tokens/sec, 98% accuracy)

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

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

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

Unit and integration test execution and validation

Analyze Claude Code sessions using Braintrust logs

Security vulnerability analysis and testing

Documentation, handoffs, session summaries, and ledger management

Deterministic router for math cognitive stack - maps user intent to exact CLI commands

Document the codebase comprehensively

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

Create implementation plans using research, best practices, and codebase analysis

Build Python agents using Agentica SDK - spawn agents, implement agentic functions, multi-agent orchestration