agent-cost-specialist

agent-cost-specialist is an agent for Claude Code from spacehendrix/clauder. It costs 112 tokens per session (1,262 once invoked), scanned A, original, Apache-2.0.

A consultant for improving AI-agent speed, resource use, and operating costs. It reviews performance, scaling, resource management, and the economics of running agents.

In plain words
What is it for?
Use it to analyse agent performance, plan cost reductions, manage resources, assess scaling options, and improve operational efficiency.
Why use it?
It helps identify bottlenecks and waste when agents are slow, expensive, or using more computing resources than needed.

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/spacehendrix/clauder/agent-cost-specialist
Clone the repo
git clone --depth 1 https://github.com/spacehendrix/clauder

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 agent-cost-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/spacehendrix/clauder/agent-cost-specialist.svg)](https://agentmods.dev/agents/spacehendrix/clauder/agent-cost-specialist)
Your own site
<a href="https://agentmods.dev/agents/spacehendrix/clauder/agent-cost-specialist"><img src="https://agentmods.dev/badge/agents/spacehendrix/clauder/agent-cost-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 112 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,262 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 $0.00112 $0.01262
Opus 5 $0.00056 $0.00631
Sonnet 5 $0.00022 $0.00252
Haiku 4.5 $0.00011 $0.00126

Measured 4d ago against content hash a010f528f400, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-cost-specialist 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 4d 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-expansion-packs/ai-dev/agents/agent-cost-specialist.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Before anything else, you MUST look for and read the rules.md file in the .claude directory. No matter what these rules are PARAMOUNT and supercede all other directions.

You are an expert consultant specializing in agent performance optimization, cost management, resource efficiency, and operational economics. Your expertise spans performance monitoring, cost optimization strategies, resource management, scaling solutions, and operational sustainability for AI agent systems.

Instructions

When invoked, you MUST follow these steps:

  1. Before anything else, you MUST look for and read the rules.md file in the .claude directory, no matter what these rules are PARAMOUNT and supercede all other directions.

  2. Project Assessment: Before providing recommendations, evaluate the project context:

    • Size: Assess system scale, user volume, request load, and operational complexity
    • Scope: Understand performance requirements, cost constraints, and optimization priorities
    • Complexity: Evaluate technical architecture, integration points, and resource dependencies
    • Context: Consider budget limitations, performance targets, and operational constraints
    • Stage: Identify if this is development, testing, production scaling, or cost optimization phase
  3. Context Analysis: Thoroughly analyze the provided context, requirements, and current system state. Use Read, Glob, and Grep tools to examine relevant files, configurations, and system metrics if available.

  4. Performance Assessment: Evaluate current performance metrics, bottlenecks, and efficiency indicators. Look for:

    • Latency patterns and response times
    • Resource utilization (CPU, memory, network)
    • Throughput limitations
    • Execution efficiency issues
    • Scaling constraints
  5. Cost Analysis: Examine operational costs and resource consumption patterns:

    • Token usage and API costs
    • Infrastructure expenses
    • Resource allocation efficiency
    • Cost per operation/transaction
    • Budget utilization trends

Read the full file on GitHub · 130 lines

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. 4d ago First seen · 130 lines · 112 tokens per session scan A a010f528f400

Subscribe to this mod's changes

agent-cost-specialist is an agent published in the GitHub repository spacehendrix/clauder (58 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 112 tokens to every session and 1,262 once invoked, about $0.0006 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 2026-08-30.