Impl Testing — Testing & QA agent for Claude Code
Reviews implementation plans from a testing strategy perspective.
How to install Impl Testing
Installs to ~/.claude/agents/pinecone-io-rings-impl-testing.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/pinecone-io/rings/HEAD/.claude/agents/impl-testing.md -o ~/.claude/agents/pinecone-io-rings-impl-testing.md Restart Claude Code, or start a new session, for it to be picked up.
What Impl Testing does
name: impl-testing model: sonnet description: Reviews implementation plans from a testing strategy perspective. Use when evaluating test coverage, mock design, unit vs. integration test balance, test isolation, and whether the proposed implementation will be easy or hard to test.
You are an experienced developer who thinks carefully about test strategy. You know that tests that are hard to write are a sign of a design problem, that mocks are a tool to be used carefully, and that the rig
Alternatives in Testing & QA
- Gitnexus Test CI Verifier — GitNexus test and CI reviewer 45.8k ★
- Civitai Test Review — Reviews the tests in a feature segment of the main Civitai Next.js app (src/) for whether they would actually 7.2k ★
- Arbiter — You are a specialized validation agent 3.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
QA Release
Manages quality gates, test planning, regression confidence, and release readiness. Use when testing, creating
Gadfly
Hostile product skeptic. Stress-tests features and plans from the user's perspective. Use before CTO when prod
QA Strategist
Use this agent for read-only test-coverage gap analysis between waves. Identifies missing boundary cases, erro
Test Documenter
Use this agent to document existing automated tests - classifying each as Unit, Mock, Integration, or E2E and
Spec Critic
Adversarial reviewer for implementation plans and specs. Evaluates whether a plan will actually work when hand
Task Planner.Agent
Translates a task into a minimal, executable implementation plan with scoped steps, risks, and a test strategy
Related Skills
Evidence Verify Gate
You are auditing a proposed skill edit for cluster 0. The edit was inferred from a cluster of FAILING agent tr
Pde Loop
Brainstorm product ideas and have a different model grade them, so the model that proposed an idea never decid
Agent Strategy Mode
Adaptive agent behavior via strategy presets + stagnation detection. Prevents repair loops. Tune innovate/hard