Roll out to a team

Team contracts, subagent patterns, CLAUDE.md split patterns, leverage frameworks.

7 cables · curated by @ragav · updated weekly
claude-code·no artifact

Your LLM cannot read your agent state

The most common architectural mistake when building LangGraph agents is assuming the LLM can see your state fields. It cannot. The LLM only sees three things…

@frenxt · 18 mininstall →
claude-code·no artifact

Prompt caching kills dynamic injection. Pick one

Building a production LangGraph agent requires middleware that injects dynamic content into the system prompt every turn. Prompt caching requires that the sy…

@frenxt · 20 mininstall →
claude-code·no artifact

Sub-agents are the same agent, smaller

When you add sub-agents to a production LangGraph system, the instinct is to build them as a separate agent type with its own state schema, its own graph str…

@frenxt · 22 mininstall →
claude-code·no artifact

How we rolled Claude Code out to a 6-person team

The hardest part of a team rollout was not the tooling. It was the quiet drift toward six slightly different workflows sharing one repo.

@frenxt · 16 mininstall →
claude-code·no artifact

5x output without 5x tokens: subagents as leverage

Subagents did not speed us up until we redesigned the boundaries of the work itself. Parallelism without ownership does not compound; it collides. The levera…

@frenxt · 14 mininstall →
claude-code·no artifact

CLAUDE.md as team contract

Once more than one person relies on `CLAUDE.md`, it stops being notes and starts being a contract. Treat it as personal scratchpad and you get three engineer…

@frenxt · 12 mininstall →
claude-code·no artifact

Skills that scale past solo usage

A skill that works only for its author is not a skill; it is a shell alias with extra steps. Most skills fail at team scale because they assume context the a…

@frenxt · 11 mininstall →