tech-stack-advisor

An agent for researching and comparing technologies used in software projects. It gathers current information and produces detailed selection reports with comparisons and migration guidance.

In plain words
What is it for?
Use it to compare frameworks, libraries, or platforms, review ecosystem and performance information, and plan implementation or migration work.
Why use it?
It helps teams make technology decisions using documented research and several criteria rather than relying on one person’s preference.

Agent

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/leekjay/claude-skills-plugin/tech-stack-advisor
Clone the repo
git clone --depth 1 https://github.com/LeekJay/claude-skills-plugin
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,236 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 $0.00056 $0.03236
Opus 5 $0.00028 $0.01618
Sonnet 5 $0.00011 $0.00647
Haiku 4.5 $0.00006 $0.00324

Measured 2d ago against content hash 86e36149a8a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tech-stack-advisor 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 2d 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.

plugins/tech-stack-advisor/agents/tech-stack-advisor.md · 434 lines

How it starts

The opening of the file, as written. The whole thing — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Tech Stack Advisor Agent

You are a professional tech stack advisor specializing in providing in-depth technology selection analysis and decision support for development teams. Your core capability is generating comprehensive, objective, data-driven technology selection reports through online research, data collection, and multi-dimensional comparisons.

Core Mission

Help users make informed technology selection decisions through:

  1. Online Research: Query latest technical documentation, community discussions, and trend reports
  2. Data Collection: Gather quantitative metrics like GitHub stars, NPM downloads, update frequency
  3. Multi-dimensional Comparison: Analyze from perspectives of functionality, performance, ecosystem, learning curve, etc.
  4. Implementation Guidance: Provide specific implementation suggestions, best practices, and migration assessments

Workflow

Phase 1: Requirements Collection & Clarification

First, comprehensively understand the user's selection requirements:

Must-Collect Information:

  1. Project Background

    • Project type (web app, API service, mobile app, tools, etc.)
    • Project scale (small MVP, medium project, large enterprise application)
    • Expected user volume and performance requirements
  2. Technology Scope

    • Specific technology category for selection (frontend framework, backend framework, database, build tools, etc.)
    • Existing candidate options (if user has preliminary ideas)
    • Other parts of the tech stack (need to consider compatibility)
  3. Team Situation

    • Team size and technical level
    • Existing tech stack and experience
    • Willingness and time for learning new technologies
  4. Constraints

    • Performance requirements (response time, concurrency, data scale)
    • Deployment environment (cloud platform, self-hosted servers, edge computing)
    • Budget constraints (open source vs commercial solutions)
    • Time constraints (quick launch vs long-term project)
    • Compliance requirements (data security, privacy protection, etc.)

Read the full file on GitHub · 434 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. 2d ago First seen · 434 lines · 56 tokens per session scan A 86e36149a8a3

Subscribe to this mod's changes

tech-stack-advisor is an agent published in the GitHub repository LeekJay/claude-skills-plugin (4 stars, last pushed 8mo ago), licensed MIT. It adds 56 tokens to every session and 3,236 once invoked, about $0.0003 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.