Getty

Knarr Test Writer — Testing & QA agent for Claude Code

Testing & QA community

Write Knarr tests with Test2::V0 and the Handler::Code fake handler — protocol round-trips, streaming end markers, routing/passthrough behavior.

How to install Knarr Test Writer

Installs to ~/.claude/agents/getty-langertha-knarr-knarr-test-writer.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Getty/langertha-knarr/HEAD/.claude/agents/knarr-test-writer.md -o ~/.claude/agents/getty-langertha-knarr-knarr-test-writer.md

Restart Claude Code, or start a new session, for it to be picked up.

What Knarr Test Writer does

name: knarr-test-writer description: "Write Knarr tests with Test2::V0 and the Handler::Code fake handler — protocol round-trips, streaming end markers, routing/passthrough behavior. Tests never require live API keys. Use for test additions, regression scaffolding, and coverage of new handlers or protocols." model: sonnet briefing: skills: - getty-perl-core - perl-ai-langertha - perl-io-async-future - kanban-issues-karr-ticket

You are the knarr-test-writer for **Knarr,

Alternatives in Testing & QA

  • Gitnexus Test CI Verifier — GitNexus test and CI reviewer 45.8k ★
  • Debugger — Debugging specialist for errors, test failures, and unexpected behavior 2.8k ★
  • Lens Reviewer — Use this agent for severity-rated code review with 2-stage protocol (spec compliance first, then code quality) 523 ★

Full documentation available on GitHub

View Source Repository

Related Agents

Raider Test Writer — Testing & QA agent for Claude Code

Raider Test Writer

Write Langertha::Raider tests with Test2::V0 — agent loop, MCP tool calling, CLI/Hall/ACP behavior. Tests neve

Testing & QA community
AI Provider Author — Testing & QA agent for Claude Code

AI Provider Author

WRITE-access implementer for AI provider integrations, model routing, embeddings, prompt systems, streaming, a

Testing & QA community
Parallel Hunt Finder — Testing & QA agent for Claude Code

Parallel Hunt Finder

Finder for a /parallel-hunt round — investigates the live system for real defects, writes evidence and a faili

Testing & QA community
Test Authenticator — Testing & QA agent for Claude Code

Test Authenticator

Detects fake, theatrical, and meaningless tests. Use PROACTIVELY after test suites are written to catch mock-e

Testing & QA community
Knarr Worker — Testing & QA agent for Claude Code

Knarr Worker

Default Knarr worker — implement, refactor, debug, and test code in the Langertha-Knarr LLM proxy distribution

Testing & QA community
Observer Lite — Testing & QA agent for Claude Code

Observer Lite

Lightweight code quality observer. Runs 4 quick checks: secrets scan, test gaps, silent failures, debt markers

Testing & QA community

Related Skills

Pi Workbench — Development skill for Claude Code

Pi Workbench

Native desktop workbench (PySide6) for the pi coding agent — streaming chain-of-thought, per-turn token/cache/

Development community
Triton Fused Epilogue Kernels — Development skill for Claude Code

Triton Fused Epilogue Kernels

Fuse epilogue ops (normalization, gating, residual, activation, dropout) into Triton attention/matmul kernels

Development community
Local Memory — AI skill for Claude Code

Local Memory

100% local, OpenAI-compatible memory layer for AI agents. On-device embeddings via Ollama + SQLite (sqlite-vec

AI community