Agent Engineering Labs

Write a Context File That Stops Invented Conventions

Measure how often an agent invents commands or patterns in your repo, then write a short AGENTS.md that fixes it — and prove it with before/after runs.

Cursor · Claude Code · OpenAI Codex · GitHub Copilot

One SKILL.md That Triggers in Claude Code and Cursor

Write a release-notes skill with a script and a reference file, install it in two tools from one source, and tune the description until it triggers reliably.

Claude Code · Cursor · OpenAI Codex

Build an MCP Server Whose Idle Schema Stays Small

Wrap an internal API as an MCP server with three well-designed tools instead of fifteen thin ones, measure the idle token cost, and connect it to two clients.

Cursor · Claude Code · OpenAI Codex · LangChain / LangGraph

A Hook That Blocks Commits When Tests Were Skipped

Write a pre-tool hook that intercepts git commit, checks that the test command ran successfully after the last edit, and blocks with a clear message if not.

Claude Code · Cursor

Implementer + Reviewer Subagent Split

Define a read-only reviewer subagent with a bug-hunting prompt, run it after the main agent implements a feature, and compare bugs found against self-review.

Claude Code · Cursor · GitHub Copilot

Three Agents in Parallel on Git Worktrees

Split a small milestone into three independent tasks, run one agent per worktree at the same time, and review three PRs — measuring wall-clock time against doing them one by one.

Cursor · Claude Code · OpenAI Codex

Map a Claude Plugin Into an OpenClaw Bundle

Take a Claude Code plugin with skills, a command, and an MCP server, install it into OpenClaw as a bundle, and trigger it from a chat channel.

OpenClaw · Claude Code

LangGraph Interrupt Before a Write Tool

Build a support agent that drafts refunds, pauses with interrupt() for human approval, resumes on the same thread, and never double-charges on resume.

LangChain / LangGraph

Build a PR Review Agent With an SDK and Run It in CI

Write a small read-only review agent with the Claude Agent SDK or Cursor SDK, give it your team's review checklist as a skill, and run it on every pull request in GitHub Actions.

Claude Code · Cursor · OpenAI Codex

Golden-Task Eval for a Skill Change

Build a small harness that runs golden tasks against a skill several times, scores activation and outcome, and gates skill changes in CI.

Claude Code · Cursor · OpenAI Codex · LangChain / LangGraph