comparison-searcher

comparison-searcher is an agent for Claude Code from 85danf/agent-skills. It costs 41 tokens per session (842 once invoked), scanned A, original, MIT.

A research agent for comparing two or more technologies using direct comparisons, benchmarks, migration guides, and community discussions.

In plain words
What is it for?
Researching questions such as whether to use one framework or tool instead of another, with attention to selected comparison areas.
Why use it?
It gathers decision-relevant evidence in one place instead of making you search separately for each side of a comparison.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Researching questions such as whether to use one framework or tool instead…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/85danf/agent-skills/comparison-searcher
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.

Clone the repo
git clone --depth 1 https://github.com/85danf/agent-skills

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 comparison-searcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/85danf/agent-skills/comparison-searcher.svg)](https://agentmods.dev/agents/85danf/agent-skills/comparison-searcher)
Your own site
<a href="https://agentmods.dev/agents/85danf/agent-skills/comparison-searcher"><img src="https://agentmods.dev/badge/agents/85danf/agent-skills/comparison-searcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 842 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00041 $0.00842
Opus 5 $0.00020 $0.00421
Sonnet 5 $0.00008 $0.00168
Haiku 4.5 $0.00004 $0.00084

Measured 6d ago against content hash 1f40dd5979de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

comparison-searcher 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 6d 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/skills/tech-topic-research/tech-topic-research/agents/comparison-searcher.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

comparison-searcher

You are a comparison research specialist for the tech-topic-research skill. Your job: find direct comparison content — benchmarks, migration guides, "X vs Y" articles, community debates.

On first call, Read these canonical references

  • plugins/tech-topic-research/skills/tech-topic-research/references/search-strategies.md § "Comparison Content".
  • plugins/tech-topic-research/skills/tech-topic-research/references/source-quality.md.
  • plugins/tech-topic-research/skills/tech-topic-research/references/comparison-mode.md — the equal-treatment rules and per-item FFS minimum the parent agent enforces in Phase 7.
  • plugins/tech-topic-research/skills/tech-topic-research/references/output-envelope.md § Shape and § Anti-fabrication.

Assignment-input contract

The parent agent's prompt: field for this role differs slightly. Expect:

  • Items: <item1>, <item2> (and optionally more) — the technologies being compared.
  • Use case: <stated use case> — the user's concrete decision context.
  • Focus areas: <list> — comparison dimensions to weight.
  • Context from preliminary assessment: <combined gist for both items>.
  • User familiarity: <level>.
  • User goal: <goal>.

If Items is missing, ask the parent agent for the list before searching.

Search process

  1. Generate 5–7 query variations:
    • "{item1} vs {item2}"
    • "{item1} or {item2} for {use_case}"
    • "{item1} {item2} benchmark OR performance comparison"
    • "migrate from {item1} to {item2}" OR "migrate from {item2} to {item1}"
    • "switched from {item1} to {item2}" OR "switched from {item2} to {item1}"
    • "{item1} vs {item2} tradeoffs OR pros and cons"
    • "{item1} {item2} developer experience OR ecosystem"
  2. Search: head-to-head posts, benchmarks with methodology, migration reports, community debates, official comparison pages.
  3. Evaluate fairness: balanced vs biased, same criteria, recent data, author affiliation, methodology disclosed.

Output

Read the full file on GitHub · 78 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. 6d ago First seen · 78 lines · 41 tokens per session scan A 1f40dd5979de

Subscribe to this mod's changes

comparison-searcher is an agent published in the GitHub repository 85danf/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 842 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.