A ralph harness for long-running AI coding tasks — a generator-evaluator loop that orchestrates Claude Code, OpenAI Codex & GitHub Copilot across repositories 🍩
CLI + TUI UX specialist for ralphctl. Use when designing OR implementing user-facing surface area — command / flag structure, Ink TUI views and prompts, multi-flow session UX, output formatting, error messages, empty-state guidance, help text, theme tokens. Owns src/application/ui/ end-to-end and makes the call on UX…
Documentation custodian for ralphctl. Use when code lands that may have outdated CLAUDE.md or anything under .claude/docs/ (ARCHITECTURE, KERNEL-DESIGN, WORKFLOWS, AI-SETTINGS, SECURITY, PERFORMANCE, REQUIREMENTS, DESIGN-SYSTEM, MANUAL-TEST-PLAYBOOK, HARNESS-PRINCIPLES, RESEARCH-REFERENCES, diagrams/); when a flow…
TypeScript implementer for ralphctl. Use for writing features, fixing bugs, refactoring, or adding tests — anywhere a code change is needed. Respects the four-module Clean Architecture layering (domain → business → integration → application), the chain framework at src/application/chain/, function-first use cases, and…
Implementation planner for ralphctl. Use BEFORE coding begins — when breaking a feature / bug / refactor into scoped, dependency-ordered tasks, identifying affected files, or sanity-checking an approach against the existing architecture. Returns a plan; never writes code.
Prompt template specialist for ralphctl. Use when authoring or editing any .md under src/integration/ai/prompts/ /template.md or src/integration/ai/prompts/partials/, when adding a new placeholder, when adjusting how templates are loaded / substituted (engine/template-loader.ts, engine/substitute.ts…
Code reviewer for ralphctl. Use AFTER implementation — to review a diff / PR / branch for correctness, bugs, architectural-layering violations (domain → business → integration → application), TypeScript nuance (generics, narrowing, Result vs throws), chain composition, and consistency with project conventions.…
Test engineer for ralphctl. Use when writing new vitest tests, shoring up coverage for a module or flow, debugging a flaky / failing test, or designing the test strategy for a new feature. Knows the project's port-based test-double patterns and the flow step-order fence tests.