Typesafe Engineer — Development agent for Claude Code
Implements TypeSafe integrations: registered QuestionSets, client wiring, answer composition in code, and live tests.
How to install Typesafe Engineer
Installs to ~/.claude/agents/herakles-dev-typesafe-claude-kit-typesafe-engineer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/herakles-dev/typesafe-claude-kit/HEAD/agents/typesafe-engineer.md -o ~/.claude/agents/herakles-dev-typesafe-claude-kit-typesafe-engineer.md Restart Claude Code, or start a new session, for it to be picked up.
What Typesafe Engineer does
name: typesafe-engineer description: "Implements TypeSafe integrations: registered QuestionSets, client wiring, answer composition in code, and live tests. Enforces that code owns the workflow and the model only judges. Use once questions exist, or to refactor an existing integration onto the shared client." model: sonnet color: green category: typesafe default_mode: subagent effort: medium triggers:
- "implement the typesafe integration"
- "wire up jev"
- "build the questionset"
- "
Alternatives in Development
- Mack — Automation Specialist 296 ★
- Pixel Art Composition Reviewer 144 ★
- Deferral Drafter — PRFlow's implement-phase Deferral-Drafter agent 115 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Typesafe Question Smith
Writes and refines the actual TypeSafe questions: atomic decomposition, primitive selection, contrastive crite
Typesafe Adversary
Red-teams TypeSafe integrations before users do. Probes the nine documented Jev failure modes, tests prompt in
Pattern Guy
Evaluates the WRITING QUALITY of changes — judges the diff against Lucas's registered patterns and clean code
Start Here
Use this agent on first run to set up a new workspace from scratch. Walks the user through identity, agent sel
Frontend Implementor Specialist
Use this agent to implement FRONTEND work — components, hooks, query layers, styling, client wiring — against
Review Production
MorviLabs review-crew specialist. Checks whether a change is safe to ship and run, on the client or the server
Related Skills
AI Engineer
Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and
Augustus
Agent skill: design judgment-assisted systems with TypeSafe Jev (System One). Maps Choice/Score/Noul onto deci
Frontloom React
Use this skill for React and Next.js frontend tasks. Enforces idiomatic React patterns including hooks, compon