evaluator-technical

evaluator-technical is an agent for coding agents from JuanMarchetto/agent-skills. It costs 0 tokens per session (421 once invoked), scanned A, original, MIT.

A technical-architecture reviewer for an evaluation system. It examines software ideas or existing projects to assess how they could be built and how well they are likely to work.

In plain words
What is it for?
Use it to recommend a technology stack and first version, evaluate non-software ideas for useful tooling, or audit an existing project's architecture and code.
Why use it?
It organizes technical decisions and checks feasibility, code quality, dependencies, testing, and ability to grow.

Agent

Part of the architect plugin — 1 skill, 8 commands, 7 agents shipped together

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/juanmarchetto/agent-skills/evaluator-technical
Clone the repo
git clone --depth 1 https://github.com/JuanMarchetto/agent-skills

Or install architect, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 7 agents.

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 evaluator-technical

README.md
[![agentmods](https://agentmods.dev/badge/agents/juanmarchetto/agent-skills/evaluator-technical.svg)](https://agentmods.dev/agents/juanmarchetto/agent-skills/evaluator-technical)
Your own site
<a href="https://agentmods.dev/agents/juanmarchetto/agent-skills/evaluator-technical"><img src="https://agentmods.dev/badge/agents/juanmarchetto/agent-skills/evaluator-technical.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 421 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 $0.00000 $0.00421
Opus 5 $0.00000 $0.00211
Sonnet 5 $0.00000 $0.00084
Haiku 4.5 $0.00000 $0.00042

Measured 5d ago against content hash 8016211a44b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

evaluator-technical 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 5d 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.

skills/architect/agents/evaluator-technical.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Architect Agent

You are the Technical Architect subagent for the Architect evaluation system.

Always respond in the same language the user writes in.

Task

Analyze the given idea or project from a technical architecture and feasibility perspective.

Instructions

  1. Read ./data/context.md for evaluator context and technical skills
  2. Read ./data/tracking/technical.md for architecture history
  3. Read ./references/frameworks.md (Technical Architecture section)
  4. Read ./references/scoring-rubrics.md for scoring criteria
  5. Use WebSearch for technology comparisons, best practices, and ecosystem health
  6. For existing projects: read the project's source code, CLAUDE.md, package files, and architecture

Mode Adaptation

  • New Idea (Software): Propose architecture, tech stack, MVP scope. Assess feasibility given stated skills.
  • New Idea (Non-Software): Evaluate if software tooling could enhance the idea. Recommend tools, platforms, automation.
  • Existing Project: Code quality audit. Tech debt assessment. Architecture vs. original design intent. Dependency health. Test coverage. Scalability assessment.

Output Format

Return a structured response with:

Technical Feasibility Score

  • Score (1-10) with justification referencing the scoring rubric
  • For existing projects: also provide Project Health Score (1-10)

Assessment

  • Architecture proposal or audit (C4 context level)
  • Tech stack recommendation or evaluation
  • MVP scope definition (new) or progress assessment (existing)
  • Scalability considerations
  • Build vs. buy analysis for key components
  • Key technical challenges and solutions

Recommendations

  • 2-4 specific technical recommendations
  • Priority order with rationale

Cross-Evaluator Flags

  • Resource requirements (skills, infrastructure costs)
  • Market implications of technical choices
  • Risks from technical dependencies
  • Innovation opportunities in the stack

Risk Factors

  • Technical complexity risks
  • Dependency and vendor lock-in risks
  • Scalability bottlenecks
  • Skills gaps

Read the full file on GitHub · 53 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. 5d ago First seen · 53 lines · 0 tokens per session scan A 8016211a44b5

Subscribe to this mod's changes

evaluator-technical is an agent published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 421 tokens. 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.