Skip to content
Anthropic Claude Code AI workflow planning workspace.
Anthropic Claude CodeClaude Code workshopWorkflow first, prompt second

Claude Code workflows that survive a real week

Claude Code is a terminal coding agent from Anthropic. It works best when the team designs the workflow around it.

Claude CodeTerminal agentToolBash · Write · EditPreToolUseLint · validate · gatePostToolUseFormat · log · auditSub-agentBackground research · audits · scansEVERY TOOL CALL · INSPECTABLE

Hooks intercept every tool call. Sub-agents run in the background.

What this is

Tool focus: Anthropic Claude Code

Workshops on Claude Code (Anthropic CLI agent) for UK engineering teams: workflow design, hooks, MCP servers, sub-agents and review discipline.

Workflow first, prompt second

Feature work, refactors, bug triage and docs are mapped first. Prompt patterns come after the workflow is clear.

Hooks and slash commands

Hooks enforce checks, formatters and validators. Slash commands cover the few recurring prompts worth standardising.

Sub-agents for boring work

Research, audits, dependency scans and test triage run in bounded sub-agents while the main session stays on the change.

How an engagement runs

  1. Day 0

    Read-only review

    Repo, CI, and current developer workflow are mapped. We agree the first hooks, sub-agents, and MCP servers worth wiring up.

  2. Day 1

    Workflow design

    Workflow design, hooks, slash commands, sub-agents, MCP short list and review patterns.

  3. Day 2

    On the real repo

    Real Claude Code sessions on agreed tasks. Hooks fire, sub-agents run, diffs land in review.

Common questions

How is this different from training people on ChatGPT?

Claude Code lives in the terminal and reads the repository. The training is about workflow design and review discipline around an agent that has access to the codebase, not about prompt phrasing for a chat box.

Do you build custom MCP servers?

Yes, where the team has a genuine internal tool worth surfacing. MCP server design has its own page; on the workshop we focus on wiring up servers that already exist or that the team can build in a day.

Will this work in a regulated environment?

It is built for one. Read-only access first, named review gates, hooks that enforce policy, and the M365 and identity layer underneath stays part of the engagement, not an afterthought.

© 2026 Magrathean UK Ltd. All rights reserved.