Claude Code MCP and team conventions
Inconsistent usage across engineers, not tool access, is what slows AI coding adoption on real teams. Shared team conventions cut that variability: repository instructions everyone follows, code review standards that set clear thresholds, and AI coding standards reinforced by examples from your own codebase. Teams then compare outcomes against a baseline instead of trading anecdotes about which prompt worked.
Why conventions beat one-off prompting
The biggest gap is not tool access. It is inconsistent usage across engineers. Shared conventions reduce variability, make review easier, and let teams compare outcomes instead of anecdotes.
What becomes standard
We define CLAUDE.md, branch and PR etiquette, review thresholds, test expectations, Claude Code MCP permissions, secret-handling rules, and escalation points for risky architectural or security decisions.
How adoption compounds
A team convention becomes useful when it is short enough to follow, visible in the repository, and reinforced by examples from the team’s own codebase.
Official references
Current product documentation we use when shaping this training topic.
Selected research
Representative field notes connected to this topic.
Claude Code hooks and team conventions
A practical guide to claude code hooks documentation, CLAUDE.md, MCP, and reviewable team conventions.
Claude Code MCP team conventions
Practical Claude Code guidance for claude mcp, CLAUDE.md, hooks, and reviewable team conventions.
Claude Code team conventions
Claude Code teams need one shared way to set context, review changes, and keep agent work inside repo rules.
Claude Code team skills and conventions
Claude Code 2.1.150 tightens team conventions around claude code skills, CLAUDE.md, hooks, and shared repo context.
Claude Code 2.1.139 team conventions
Claude Code 2.1.139 team conventions: a CLAUDE TOC, red-folder approvals, data-class tags on MCP connectors, and a weekly retro note.
Claude Code 2.1.142 team conventions
Claude Code 2.1.142 team conventions for parallel agent streams: a skill index, a hook budget, a CLAUDE TOC, and red-folder approvals.
Related training topics
Bring this into your team
We tailor the training to your codebase, adoption stage, and review standards.
Get in touch