dotfiles

Run `headroom perf` and act on its recommendations — flag long/unstable conversations, surface uncompressed stale reads, and publish eligible TOIN patterns

Critique React/TypeScript frontend code for correctness, security, performance, and idiomatic patterns

Execute a plan artifact's work orders by delegating each to Claude or Codex at the cheapest sufficient model tier, reviewing every result, and bouncing blocked items back to plan

Turn one scoped task or Linear issue into an implementation plan artifact of work orders, ready for `implement` to execute — no code written here

Decompose a vague goal into a prioritized, estimated roadmap and push it to Linear as epics/issues — product/principal-engineer altitude, no code

Generate atomic git commit messages following trunk-based development practices

Create or update a PR for the current branch based on actual changes. Uses av for PR management, and git/sem/codegraph for change analysis.

Structure and write a technical design document or ADR for a proposed change or new system

Edit technical articles for accuracy, clarity, structure, and practical value before publishing

Critique REST and gRPC API designs for contract correctness, backward compatibility, and operational safety

Critique CI/CD pipeline definitions for correctness, security, and build reliability

Critique data pipelines and ML code for correctness, reproducibility, train/serve skew, and operational safety

Update a project README with accurate setup, usage, commands, and repo-specific notes.

Create laconic, concise, clear technical documentation from code, notes, or rough requirements.

Create a new agent skill with proper structure, frontmatter, and focused instructions

Generate a focused system prompt for a given problem or role

Bootstrap or update AGENTS.md and CLAUDE.md for a repo — consolidate agent instructions into README.md and make the agent files delegate to it.

Critique software architecture for scalability, reliability, security, and operational cost

Orchestrate backend code review across Go/Python, SQL, queues, and distributed storage

Critique Go code for correctness, idiomatic style, concurrency safety, and performance

Critique infrastructure-as-code (Terraform, Pulumi, Kubernetes, Docker) for security, correctness, and operational safety

Critique Python code for correctness, idiomatic style, Pythonic design, and pragmatic simplicity

Critique React code for correctness, idiomatic hooks usage, composition patterns, and rendering efficiency

Critique code and configuration for authentication, authorization, injection, secrets handling, and supply chain risks

Critique SQL schemas, migrations, and queries for correctness, safety, and performance

Critique TanStack Router and TanStack Query usage for type safety, data loading correctness, and cache management

Critique TypeScript code for type correctness, unsound patterns, and unsafe escape hatches