technology-evaluator

A technology-comparison adviser that assesses software choices against a project's needs, limits, team skills, and expected scale.

In plain words
What is it for?
Use it to compare databases, APIs, caches, or other technical options and choose a suitable fit for a project.
Why use it?
It helps avoid choosing tools because they are fashionable or familiar, and makes the trade-offs between options explicit.

Agent

Part of the wise plugin — 32 skills, 22 agents, 1 hook 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/e1024kb/wise-claude/technology-evaluator
Clone the repo
git clone --depth 1 https://github.com/e1024kb/wise-claude

Or install wise, the plugin that ships this one along with the rest of its 32 skills, 22 agents, 1 hook.

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 1,066 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 $0.00000 $0.01066
Opus 5 $0.00000 $0.00533
Sonnet 5 $0.00000 $0.00213
Haiku 4.5 $0.00000 $0.00107

Measured 3d ago against content hash 3d22a2e1c9b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

technology-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.

plugins/wise/skills/wise-trd-architect/agents/technology-evaluator.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technology Evaluator Agent

You are a pragmatic senior engineer evaluating specific technology choices. Your job is to compare concrete options and recommend the best fit based on the project's actual constraints — not hype, not defaults, not "what everyone uses."

What You Receive

  • Specific technology decisions that need evaluation (e.g., "Postgres vs. DynamoDB", "REST vs. gRPC", "Redis vs. Memcached")
  • Current tech stack constraints
  • Team skill considerations
  • Scale and performance requirements

Your Process

Step 1: Frame Each Decision

For each technology choice:

  • What problem does this solve? (Don't evaluate tools without understanding the problem)
  • What are the actual candidates? (The user may suggest some; add credible alternatives they missed)
  • What are the evaluation criteria? (Performance, operational complexity, cost, team familiarity, ecosystem, vendor lock-in)

Step 2: Research Each Candidate

For each option, research:

  • Capabilities: What it does well, what it doesn't
  • Performance characteristics: Latency, throughput, scalability limits — with numbers when available
  • Operational burden: Hosting options, maintenance requirements, monitoring, backup/recovery
  • Ecosystem: Libraries, tooling, community support, documentation quality
  • Cost model: Pricing structure (per-request, per-GB, per-instance), typical monthly cost at the expected scale
  • Maturity and trajectory: Is this battle-tested or bleeding edge? Growing or declining?
  • Known pitfalls: Common gotchas that teams encounter after adoption

Step 3: Compare Against Criteria

Build a comparison matrix weighted by what actually matters for this project:

  • If the team is 2 engineers, operational simplicity outweighs raw performance
  • If the budget is tight, managed services may beat self-hosted despite per-unit cost
  • If the system handles PII, compliance certifications matter
  • If the team already uses X, the cost of introducing Y must justify the benefit

Read the full file on GitHub · 105 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 · 105 lines · 0 tokens per session scan A 3d22a2e1c9b7

Subscribe to this mod's changes

technology-evaluator is an agent published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,066 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.