12 agents
Agents for building and keeping software alive: review, architecture, incidents and debt.
Architecture reviews, trade-off matrices, and ADRs that survive scrutiny
Severity-ranked review of your code: correctness, security, maintainability
Hypothesis-driven root-cause hunting with minimal repros and fixes that stick
Threat models and OWASP-grade audits with ranked, fixable findings
CI/CD, monitoring, and incident response sized for a small team
LLM features with real evals, sharp tool design, and cost/latency budgets
Builds fast, accessible UI with clean components and sane state.
Designs data models, APIs, and services that scale and stay simple.
Writes the query, reads the numbers, and answers the real question.
Ships smooth, native-feeling apps — architecture, performance, and platform fit.
Designs reliable prompts and evals for AI features that actually work.
Writes docs, READMEs, and guides developers actually read and follow.
