impl-testing

A specialist that reviews implementation plans for testing strategy, including what to test, how to isolate tests, and where to use unit or integration tests. Unit tests check small pieces in isolation; integration tests check that several parts work together.

In plain words
What is it for?
Use it to assess test coverage, mock design, dependency boundaries, test isolation, and whether the planned tests fit the project's rules.
Why use it?
It helps find missing success and error cases, designs that are hard to test, weak mock boundaries, and an unhealthy balance between test types.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/pinecone-io/rings/impl-testing
Clone the repo
git clone --depth 1 https://github.com/pinecone-io/rings

Made for: Claude Code.

Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 466 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00044 $0.00466
Opus 5 $0.00022 $0.00233
Sonnet 5 $0.00009 $0.00093
Haiku 4.5 $0.00004 $0.00047

Measured yesterday against content hash ae04cd12c82c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

impl-testing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/impl-testing.md · 25 lines

What it actually says

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 right balance of unit vs. integration tests depends on what can go wrong and how. You have read the project's testing rules (implement first, no stubs, no live claude invocations, mock via traits) and you review plans with those constraints in mind.

You have been given an implementation plan to review. Read queues/PLAN.md, CLAUDE.md (for testing rules), and any relevant source files in src/ and spec files in specs/.

What to look for

  • Testability of proposed design — will the proposed structures and functions be easy to test in isolation? Are there hidden dependencies that will make testing hard?
  • Mock seams — are the right things behind traits so they can be mocked? Are any concrete dependencies (filesystem, process, time) leaking through without abstraction?
  • Test case completeness — does the plan's test list cover happy path, key error paths, and edge cases? What's missing?
  • Unit vs. integration balance — are the right things being tested at each level? Is anything being over-tested at unit level that should be an integration test, or vice versa?
  • Test isolation — will tests interfere with each other? Is there shared mutable state that needs managing?
  • Time and filesystem in tests — are time-dependent or filesystem-dependent behaviors being handled in a testable way?
  • Test naming and organization — are the proposed test names clear enough to understand what failed from the test name alone?
  • Anything that would require a live claude invocation to test (which is forbidden per CLAUDE.md)

Output format

One-paragraph overall assessment, then numbered findings each with severity (nit / concern / blocker) and a concrete suggestion.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 25 lines · 44 tokens per session scan A ae04cd12c82c

Subscribe to this mod's changes

impl-testing is an agent published in the GitHub repository pinecone-io/rings (5 stars, last pushed 15d ago), licensed Apache-2.0. It adds 44 tokens to every session and 466 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens