Agent Cursor
Assesses blast radius of changes to shared packages (packages/shared, libs/dal, libs/application-generic). Use proactively before modifying shared code to identify downstream consumers that may break.
24 tagged email, measured the same way as everything else here.
Browse within: api 8calendar 8
Agent Cursor
Assesses blast radius of changes to shared packages (packages/shared, libs/dal, libs/application-generic). Use proactively before modifying shared code to identify downstream consumers that may break.
Agent Cursor
Validates completed work. Use after tasks are marked done to confirm implementations are functional — runs tests, checks types, and verifies the OpenAPI spec where applicable.
Agent Claude Code
Use when implementation is complete and PR-ready to review the current diff for security, DRY opportunities, simplicity, and abstraction quality.
Agent
Inspect or update Inbox Zero rules and analytics through the public API CLI. Use when tasks involve rules, stats, or API-driven automation.
Agent
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
Agent
Issues and PRDs for this repo live as GitHub issues in kannon-email/kannon. Use the gh CLI for all operations.
Agent
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
Agent Claude Code
This directory contains specialized agents for the Nylas CLI codebase.
Agent Claude Code
Expert polyglot code writer for Go, JavaScript, and CSS. Writes production-ready code following project patterns. Use PROACTIVELY for implementation tasks.
Agent Claude Code
Explores codebase for context without coding - returns concise summaries. Supports thoroughness levels (quick, medium, thorough).
Agent Cursor
Run all CI checks locally and systematically fix any failures. Replicates GitHub workflow validations.
Agent Cursor
Debugging specialist for errors and test failures. Use when encountering issues.
Agent Cursor
Validates completed work. Use after tasks are marked done to confirm implementations are functional.
Agent Claude Code
Read-only reviewer for one narrow lens over a full workspace diff.
Agent Claude Code
Implements a single PLAN.md task in TypeScript (Next.js or Bun). Builds and self-tests; never commits unless told. Dispatched by /build-loop.
Agent Claude Code
Read-only code + security gate for a single built task (TypeScript, Next.js or Bun). Returns PASS or FAIL with findings. Dispatched by /build-loop.