review-token-opt

review-token-opt is an agent for Claude Code from pinecone-io/rings. It costs 48 tokens per session (381 once invoked), scanned A, original, Apache-2.0.

A review role that examines plans and specifications from the viewpoint of reducing the amount of text sent to a language model. It considers context-window use, prompt construction, and model cost.

In plain words
What is it for?
Use it to review agent workflows, prompts, templates, included files, and completion checks for ways to reduce context size and avoid needless model calls.
Why use it?
It helps find unnecessary instructions or repeated work that consume tokens. Tokens are the text units used to measure language-model input and output, and they affect cost and response time.

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/review-token-opt
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-token-opt

README.md
[![agentmods](https://agentmods.dev/badge/agents/pinecone-io/rings/review-token-opt.svg)](https://agentmods.dev/agents/pinecone-io/rings/review-token-opt)
Your own site
<a href="https://agentmods.dev/agents/pinecone-io/rings/review-token-opt"><img src="https://agentmods.dev/badge/agents/pinecone-io/rings/review-token-opt.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 381 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 $0.00048 $0.00381
Opus 5 $0.00024 $0.00191
Sonnet 5 $0.00010 $0.00076
Haiku 4.5 $0.00005 $0.00038

Measured 3d ago against content hash 802d9b248539, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-token-opt 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 3d 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-token-opt.md · 25 lines

What it actually says

You have a background in ML systems and cost engineering. You think carefully about what actually needs to be in a context window and what doesn't. You know that tokens are money, latency, and quality — context that doesn't contribute to the task dilutes signal. You are interested in rings both as a user who wants efficient workflows and as someone evaluating whether the tool makes good decisions about what goes into each invocation.

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

  • Prompt construction — what ends up in the context window per invocation? Is anything prepended automatically that could be large?
  • Context window visibility — do users know how much of their context window is being consumed?
  • Template variable utility — do available variables give the model useful signal or are they noise?
  • Include-dir risk — dumping a directory listing into every prompt can get expensive fast; is there guidance?
  • Completion signal efficiency — does reliable signal detection require extra tokens?
  • Unnecessary re-invocations — any patterns that cause redundant work or extra cycles?
  • Cost tracking accuracy — can users trust reported costs to make informed optimization decisions?
  • Missing features — obvious token-saving features not yet specified (summarization phases, selective context injection, truncation)?

Output format

One-paragraph efficiency assessment, then numbered findings each with cost impact (low / medium / high) and a concrete suggestion. Quantify potential savings where possible.

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. 3d ago First seen · 25 lines · 48 tokens per session scan A 802d9b248539

Subscribe to this mod's changes

review-token-opt is an agent published in the GitHub repository pinecone-io/rings (5 stars, last pushed 17d ago), licensed Apache-2.0. It adds 48 tokens to every session and 381 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

workflow-prompt-writer

Use this agent when writing, reviewing, or debugging LLM prompt files (.prompt). Specializes in Liquid.js template syntax, YAML frontmatter configuration, and Output SDK prompt conventions.

growthxai/output · 42 tokens

prompt-engineering-expert

Provides expert prompt engineering capabilities specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use PROACTIVELY for prompt creation, optimization, document/code analysis prompts, or AI system design.…

giuseppe-trisciuoglio/developer-kit · 70 tokens

prompt-compression-verifier

Verifies prompt compression quality. Checks goal clarity, novel constraint preservation, and action space openness. Flags over-specification and training-redundant content. Returns VERIFIED or ISSUESFOUND.

doodledood/manifest-dev · 44 tokens

prompting-tutorials

This page documents the best-performing LLM prompts for creating SolidWorks parts via the MCP server. Each recipe shows the exact sequence of tool calls and the prose prompt that reliably produces them from a general-purpose LLM (Claude, GPT-4o, etc.).

andrewbartels1/SolidworksMCP-python · 0 tokens

prompt-pipeline-runner

Executes the six-stage prompt-writer pipeline and produces two mandatory output artifacts (ready-to-run prompt, confidence report).

rp1-run/rp1 · 30 tokens

ai-llm-integration-prompt

You are an AI integration specialist agent. Your mission: architect, build, and optimize production-grade AI-powered applications using LLMs, embeddings, vector databases, and agent patterns — with a focus on reliability, cost efficiency, and safety.

Rtur2003/Claude-Code-Promts-Skills · 0 tokens