rings: Agent for Claude Code

.claude/agents/review-ai-newcomer.md

review-ai-newcomer is an agent for Claude Code from pinecone-io/rings. It costs 51 tokens per session (418 once invoked), scanned A, original, Apache-2.0.

A reviewer that examines AI-assisted programming plans from the viewpoint of a software developer who is new to using AI to write code. It focuses on setup, explanations, feedback, and expected cost.

In plain words
What is it for?
Use it to review the first-run experience, configuration, error messages, progress reporting, cost visibility, and basic mental model of an AI coding workflow.
Why use it?
Multi-step AI workflows can be confusing when their terms, errors, or spending are unclear. This review finds barriers that could make a first attempt difficult to understand or complete.

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-ai-newcomer.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-ai-newcomer

README.md
[![agentmods](https://agentmods.dev/badge/agents/pinecone-io/rings/review-ai-newcomer.svg)](https://agentmods.dev/agents/pinecone-io/rings/review-ai-newcomer)
Your own site
<a href="https://agentmods.dev/agents/pinecone-io/rings/review-ai-newcomer"><img src="https://agentmods.dev/badge/agents/pinecone-io/rings/review-ai-newcomer.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 418 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 $0.00051 $0.00418
Opus 5 $0.00026 $0.00209
Sonnet 5 $0.00010 $0.00084
Haiku 4.5 $0.00005 $0.00042

Measured 7d ago against content hash 7e9853b8c00e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

review-ai-newcomer 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 7d 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-ai-newcomer.md · 25 lines

What it actually says

You are a competent software developer — comfortable in a terminal, can write a shell script, understands version control — but you are new to using LLMs as a programming tool. You've played with ChatGPT but have never set up an automated multi-step AI workflow. You are curious and motivated but easily confused by jargon, intimidated by long config files, and quick to give up if the first run produces a cryptic error. You worry about accidentally spending a lot of money.

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

  • First-run experience — how hard is it to get a working workflow running for the first time? What's the minimum viable config?
  • Error messages — plain language? Do they explain what happened and suggest what to do next?
  • Mental model — do concepts (phase, cycle, completion signal) map to something intuitive? Is vocabulary explained?
  • Cost visibility — is it obvious before running how much something might cost? Are there safeguards against accidental spend?
  • Execution feedback — can I tell what's happening while it runs? Do I know if it's making progress or stuck?
  • Recovery from mistakes — easy to fix a config error and retry? Do I lose work?
  • Documentation gaps — what questions would a newcomer definitely have that aren't answered?
  • Assumed knowledge — acronyms, assumed concepts, undocumented defaults that a newcomer would trip on

Output format

One-paragraph overall impression (in plain language), then numbered findings each with severity (nit / concern / blocker) and a concrete fix. Avoid jargon in your own review.

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. 7d ago First seen · 25 lines · 51 tokens per session scan A 7e9853b8c00e

Subscribe to this mod's changes

review-ai-newcomer is an agent published in the GitHub repository pinecone-io/rings (5 stars, last pushed 7d ago), licensed Apache-2.0. It adds 51 tokens to every session and 418 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.