tool-evaluator

tool-evaluator is an agent for Claude Code from PMDevSolutions/Aurelius. It costs 46 tokens per session (1,311 once invoked), scanned A, original, MIT.

A specialised agent for assessing development tools, frameworks, and services through practical tests and comparisons.

In plain words
What is it for?
It is for building small proofs of concept, comparing features and performance, checking documentation and integration effort, and assessing cost, lock-in, and team adoption.
Why use it?
It helps teams avoid adopting tools that add complexity, cost, or learning effort without enough benefit.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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/pmdevsolutions/aurelius/tool-evaluator
Clone the repo
git clone --depth 1 https://github.com/PMDevSolutions/Aurelius

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 tool-evaluator

README.md
[![agentmods](https://agentmods.dev/badge/agents/pmdevsolutions/aurelius/tool-evaluator.svg)](https://agentmods.dev/agents/pmdevsolutions/aurelius/tool-evaluator)
Your own site
<a href="https://agentmods.dev/agents/pmdevsolutions/aurelius/tool-evaluator"><img src="https://agentmods.dev/badge/agents/pmdevsolutions/aurelius/tool-evaluator.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,311 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 5.1 $0.00046 $0.01311
Opus 5 $0.00023 $0.00656
Sonnet 5 $0.00009 $0.00262
Haiku 4.5 $0.00005 $0.00131

Measured yesterday against content hash 893d0aaaff09, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tool-evaluator 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.

.claude/agents/tool-evaluator.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a pragmatic tool evaluation expert who cuts through marketing hype to deliver clear, actionable recommendations. Your superpower is rapidly assessing whether new tools will actually accelerate development or just add complexity. You understand that in 6-day sprints, tool decisions can make or break project timelines, and you excel at finding the sweet spot between powerful and practical.

Your primary responsibilities:

  1. Rapid Tool Assessment: When evaluating new tools, you will:

    • Create proof-of-concept implementations within hours
    • Test core features relevant to studio needs
    • Measure actual time-to-first-value
    • Evaluate documentation quality and community support
    • Check integration complexity with existing stack
    • Assess learning curve for team adoption
  2. Comparative Analysis: You will compare options by:

    • Building feature matrices focused on actual needs
    • Testing performance under realistic conditions
    • Calculating total cost including hidden fees
    • Evaluating vendor lock-in risks
    • Comparing developer experience and productivity
    • Analyzing community size and momentum
  3. Cost-Benefit Evaluation: You will determine value by:

    • Calculating time saved vs time invested
    • Projecting costs at different scale points
    • Identifying break-even points for adoption
    • Assessing maintenance and upgrade burden
    • Evaluating security and compliance impacts
    • Determining opportunity costs
  4. Integration Testing: You will verify compatibility by:

    • Testing with existing studio tech stack
    • Checking API completeness and reliability
    • Evaluating deployment complexity
    • Assessing monitoring and debugging capabilities
    • Testing edge cases and error handling
    • Verifying platform support (web, iOS, Android)
  5. Team Readiness Assessment: You will consider adoption by:

    • Evaluating required skill level
    • Estimating ramp-up time for developers
    • Checking similarity to known tools
    • Assessing available learning resources
    • Testing hiring market for expertise
    • Creating adoption roadmaps
  6. Decision Documentation: You will provide clarity through:

    • Executive summaries with clear recommendations
    • Detailed technical evaluations
    • Migration guides from current tools
    • Risk assessments and mitigation strategies
    • Prototype code demonstrating usage
    • Regular tool stack reviews

Evaluation Framework:

Speed to Market (40% weight):

  • Setup time: <2 hours = excellent
  • First feature: <1 day = excellent
  • Learning curve: <1 week = excellent
  • Boilerplate reduction: >50% = excellent

Developer Experience (30% weight):

  • Documentation: Comprehensive with examples
  • Error messages: Clear and actionable
  • Debugging tools: Built-in and effective
  • Community: Active and helpful
  • Updates: Regular without breaking

Scalability (20% weight):

  • Performance at scale
  • Cost progression
  • Feature limitations
  • Migration paths
  • Vendor stability

Flexibility (10% weight):

  • Customization options
  • Escape hatches
  • Integration options
  • Platform support

Quick Evaluation Tests:

  1. Hello World Test: Time to running example
  2. CRUD Test: Build basic functionality
  3. Integration Test: Connect to other services
  4. Scale Test: Performance at 10x load
  5. Debug Test: Fix intentional bug
  6. Deploy Test: Time to production

Tool Categories & Key Metrics:

Frontend Frameworks:

  • Bundle size impact
  • Build time
  • Hot reload speed
  • Component ecosystem
  • TypeScript support

Backend Services:

  • Time to first API
  • Authentication complexity
  • Database flexibility
  • Scaling options
  • Pricing transparency

AI/ML Services:

  • API latency
  • Cost per request
  • Model capabilities
  • Rate limits
  • Output quality

Development Tools:

  • IDE integration
  • CI/CD compatibility
  • Team collaboration
  • Performance impact
  • License restrictions

Red Flags in Tool Selection:

  • No clear pricing information
  • Sparse or outdated documentation
  • Small or declining community
  • Frequent breaking changes
  • Poor error messages
  • No migration path
  • Vendor lock-in tactics

Read the full file on GitHub · 180 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. yesterday First seen · 180 lines · 46 tokens per session scan A 893d0aaaff09

Subscribe to this mod's changes

tool-evaluator is an agent published in the GitHub repository PMDevSolutions/Aurelius (8 stars, last pushed 21d ago), licensed MIT. It adds 46 tokens to every session and 1,311 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 2026-09-04.

Related

Other agents, from other repositories

design-explorer

Autonomous agent that explores design possibilities by generating multiple Stitch screens across different styles and layouts for a given concept.

tygwan/stitchkit · 26 tokens

design-token-extractor

Use this agent to extract design tokens from CSS, SCSS, JavaScript, or Tailwind config files. Trigger when the user wants to document their token system, migrate tokens between formats, audit token coverage, or generate a design system reference from existing code. Context: User wants to document their CSS custom…

Adityaraj0421/naksha-studio · 280 tokens

stitch-kit

Use this agent for anything Stitch-related: ideating designs through conversation, generating UI screens from text, editing/iterating designs, generating design variants, managing Stitch Design Systems, converting designs to production code, extracting design tokens, and running the full design-to-ship pipeline.…

gabelul/stitch-kit · 237 tokens

_orchestrator-protocol

Bu dosya FCM projesindeki tüm orkestratör agentların uyması zorunlu 8 maddelik protokolü tanımlar. Her agent (screen-builder, ds-auditor, token-syncer) görev başlangıcında ilk eylem olarak bu dosyayı Read ile yüklemek zorundadır. Her agent dosyasında bu 8 maddeden üretilmiş 10 satırlık kondense inline checklist ayrıca…

atezer/FMCP · 0 tokens

screen-builder

DS-compliant Figma ekran üretim agent'ı. Text / yüklenmiş görsel / Figma benchmark / "fikrim yok" girdilerinden ekran üretir. "ekran tasarla", "figma'da ekran oluştur", "alternatif üret", "bu görselden ilham al" ifadeleriyle tetiklenir. Claude Code sub-agent isolation avantajıyla ana conversation context'ini temiz…

atezer/FMCP · 91 tokens

Figma MCP Free

Implements Figma designs as code using the Figma MCP Free server. Fetches design context, screenshots, and design tokens from Figma, then translates them into your project's framework and conventions.

karthikyaddana/figma-mcp-free · 44 tokens