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.
npx agentmods add agents/pinecone-io/rings/impl-testinggit clone --depth 1 https://github.com/pinecone-io/ringsWhat 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.
| Model | Per session | Once 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 |
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.
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
claudeinvocation 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.
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.
- yesterday First seen · 25 lines · 44 tokens per session scan A ae04cd12c82c
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.