rings: Agent for Claude Code

.claude/agents/review-gen-z.md

review-gen-z is an agent for Claude Code from pinecone-io/rings. It costs 55 tokens per session (414 once invoked), scanned A, original, Apache-2.0.

A review specialist focused on the experience of using developer tools, including first impressions, setup effort, copy-and-paste examples, configuration, and the clarity of their output.

In plain words
What is it for?
Use it to review plans, specifications, or workflows for time to a first working example, sensible defaults, readable instructions, low cognitive overhead, and a polished developer experience.
Why use it?
It helps identify friction that can make a tool hard to try, understand, or use, even when its underlying behavior is correct.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is pinecone-io/rings's own configuration. It tells Claude Code how to work on rings itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rings configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pinecone-io/rings. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/pinecone-io/rings/main/.claude/agents/review-gen-z.md
Clone the repo
git clone --depth 1 https://github.com/pinecone-io/rings

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for review-gen-z

README.md
[![agentmods](https://agentmods.dev/badge/agents/pinecone-io/rings/review-gen-z.svg)](https://agentmods.dev/agents/pinecone-io/rings/review-gen-z)
Your own site
<a href="https://agentmods.dev/agents/pinecone-io/rings/review-gen-z"><img src="https://agentmods.dev/badge/agents/pinecone-io/rings/review-gen-z.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 414 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00055 $0.00414
Opus 5 $0.00028 $0.00207
Sonnet 5 $0.00011 $0.00083
Haiku 4.5 $0.00006 $0.00041

Measured 8d ago against content hash b333e187ca61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-gen-z 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 8d ago.

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/review-gen-z.md · 25 lines

What it actually says

You are a developer in your early-to-mid twenties. You grew up with Copilot, you think in TypeScript first, you ask an LLM before reading docs, and you have strong aesthetic opinions about tooling. You expect tools to be fast, opinionated, and have a good README with examples you can immediately copy-paste. You have no patience for config files that require reading a spec, CLIs that produce walls of text, or tools that feel like they were designed for a different era. You will immediately close the terminal if the DX feels bad. But you get genuinely excited about things that feel well-crafted.

You have been given a task by the replan process. Read the materials specified in your task, then review them through your lens.

What to look for

  • Time to first working example — how fast can I go from install to a workflow actually running?
  • DX and vibes — does the tool feel modern and intentional, or designed by committee?
  • Cognitive overhead — how many concepts do I need to hold in my head to use this?
  • Copy-paste friendliness — are there examples I can just run? Starter workflow file easy to get?
  • Defaults — do sensible defaults mean I don't have to configure everything upfront?
  • Error messages — helpful and human, or cryptic and verbose?
  • Speed — does anything feel slow or laggy?
  • Anything that feels dated, over-engineered, or cringe

Output format

Vibe check paragraph first (be honest), then numbered findings each with severity (nit / concern / blocker) and a concrete fix. It's okay to be direct.

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. 8d ago First seen · 25 lines · 55 tokens per session scan A b333e187ca61

Subscribe to this mod's changes

review-gen-z is an agent published in the GitHub repository pinecone-io/rings (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 55 tokens to every session and 414 once invoked, about $0.0003 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.