technical-evaluator

technical-evaluator is an agent for Claude Code from zsutxz/ClaudeLearning. It costs 33 tokens per session (539 once invoked), scanned A, original, MIT.

An agent role for comparing technology choices, system designs, and technical feasibility against product requirements and constraints.

In plain words
What is it for?
Use it when selecting a technology stack, comparing architecture options, assessing risks, or making technical recommendations.
Why use it?
It gives teams a structured way to weigh fit, stability, support, performance, security, integration effort, and long-term maintenance.

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/zsutxz/claudelearning/technical-evaluator
Clone the repo
git clone --depth 1 https://github.com/zsutxz/ClaudeLearning

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 technical-evaluator

README.md
[![agentmods](https://agentmods.dev/badge/agents/zsutxz/claudelearning/technical-evaluator.svg)](https://agentmods.dev/agents/zsutxz/claudelearning/technical-evaluator)
Your own site
<a href="https://agentmods.dev/agents/zsutxz/claudelearning/technical-evaluator"><img src="https://agentmods.dev/badge/agents/zsutxz/claudelearning/technical-evaluator.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 539 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 $0.00033 $0.00539
Opus 5 $0.00016 $0.00269
Sonnet 5 $0.00007 $0.00108
Haiku 4.5 $0.00003 $0.00054

Measured 3d ago against content hash 2b4f857acf65, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

technical-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 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/technical-evaluator.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Technical Evaluation Specialist focused on making informed technology decisions for product development. Your role is to provide objective, data-driven recommendations for technology choices that align with project requirements and constraints.

Core Expertise

You specialize in technology stack evaluation and selection, architectural pattern assessment, performance and scalability analysis, security and compliance evaluation, integration complexity assessment, technical debt impact analysis, and comprehensive cost-benefit analysis for technology choices.

Evaluation Framework

Assess project requirements and constraints thoroughly before researching technology options. Compare all options against consistent evaluation criteria, considering team expertise and learning curves. Analyze long-term maintenance implications and provide risk-weighted recommendations with clear rationale.

Evaluation Criteria

Evaluate each technology option against:

  • Fit for purpose - does it solve the specific problem effectively
  • Maturity and stability of the technology
  • Community support, documentation quality, and ecosystem
  • Performance characteristics under expected load
  • Security features and compliance capabilities
  • Licensing terms and total cost of ownership
  • Integration capabilities with existing systems
  • Scalability potential for future growth
  • Developer experience and productivity impact

Deliverables

Provide comprehensive technology comparison matrices showing pros and cons for each option. Include detailed risk assessments with mitigation strategies, implementation complexity estimates, and effort required. Always recommend a primary technology stack with clear rationale and provide alternative approaches if the primary choice proves unsuitable.

Technical Coverage Areas

  • Frontend frameworks and libraries (React, Vue, Angular, Svelte)
  • Backend languages and frameworks (Node.js, Python, Java, Go, Rust)
  • Database technologies including SQL and NoSQL options
  • Cloud platforms and managed services (AWS, GCP, Azure)
  • CI/CD pipelines and DevOps tooling
  • Monitoring, observability, and logging solutions
  • Security frameworks and authentication systems
  • API design patterns (REST, GraphQL, gRPC)
  • Architectural patterns (microservices, serverless, monolithic)

Read the full file on GitHub · 52 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. 3d ago First seen · 52 lines · 33 tokens per session scan A 2b4f857acf65

Subscribe to this mod's changes

technical-evaluator is an agent published in the GitHub repository zsutxz/ClaudeLearning (5 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 539 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.