search-benchmark

search-benchmark is a skill for Claude Code from agentic-community/mcp-gateway-registry. It costs 75 tokens per session (1,925 once invoked), scanned A, original, Apache-2.0.

A tool for measuring how well an AI Registry’s semantic search returns relevant results. Semantic search finds results by meaning, not only by matching exact words.

In plain words
What is it for?
Use it to build a ground-truth dataset, run more than 100 search queries against a deployed registry, evaluate ranking and recall, and create a Markdown report.
Why use it?
It provides repeatable measurements after search changes, making it easier to see whether result quality improved or declined.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python scripts/benchmark_search.py \.

Good fit Use it to build a ground-truth dataset, run more than 100 search queries against a deployed registry, evaluate ranking and recall, and create a Markdown report.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/agentic-community/mcp-gateway-registry
agentmods
npx agentmods add skills/agentic-community/mcp-gateway-registry/search-benchmark

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 search-benchmark

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentic-community/mcp-gateway-registry/search-benchmark/github.svg)](https://agentmods.dev/skills/agentic-community/mcp-gateway-registry/search-benchmark)
Your own site
<a href="https://agentmods.dev/skills/agentic-community/mcp-gateway-registry/search-benchmark"><img src="https://agentmods.dev/badge/skills/agentic-community/mcp-gateway-registry/search-benchmark/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for search-benchmark

Your own site · 80×15
<a href="https://agentmods.dev/skills/agentic-community/mcp-gateway-registry/search-benchmark"><img src="https://agentmods.dev/badge/skills/agentic-community/mcp-gateway-registry/search-benchmark.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,925 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00075 $0.01925
Opus 5 $0.00037 $0.00962
Sonnet 5 $0.00015 $0.00385
Haiku 4.5 $0.00007 $0.00193

Measured 10d ago against content hash b8fc3196d7af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

search-benchmark scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -H "Authorization: Bearer $TOKEN" "{REGISTRY_URL}/api/servers?limit=2000" > /tmp/servers.json
.claude/skills/search-benchmark/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Search Benchmark Skill

Measure semantic search quality against a deployed AI Registry. Generates a ground truth dataset from the registry's own assets, runs queries against the live API, evaluates results using standard information retrieval metrics (NDCG@10, MRR, Recall@10), and produces a markdown report.

Prerequisites

  1. Registry URL - The base URL of the deployed registry (e.g., https://d2xl2zfuhgc4l0.cloudfront.net)
  2. JWT Token - A valid admin token in .token file (get from "Get JWT Token" button in registry UI)
  3. Registry must have assets indexed - At least some servers, agents, or skills registered

The .token file supports both raw JWT format and the full JSON response from the registry UI.

Input

/search-benchmark [REGISTRY_URL] [TOKEN_FILE]
  • REGISTRY_URL - Base URL of the registry to benchmark (default: reads from user or uses http://localhost)
  • TOKEN_FILE - Path to the token file (default: .token)

Workflow

Step 1: Check for Existing Ground Truth

Check if a ground truth dataset already exists:

ls tests/fixtures/search_dataset/ground_truth.json 2>/dev/null

If the file exists, report how many queries it contains and ask the user: "A ground truth dataset already exists (N queries). Do you want to use it or generate a new one from this registry?"

  • If use existing: skip to Step 2
  • If generate new: proceed to Step 1b

Step 1b: Generate Expert Ground Truth

This is NOT a simple programmatic generation. You must deeply analyze the registry's assets and craft queries like a search expert. Follow this process:

1b.1: Fetch all assets as JSON

TOKEN=$(python3 -c "
import json
with open('{TOKEN_FILE}') as f:
    raw = f.read().strip()
if raw.startswith('{'):
    data = json.loads(raw)
    print(data.get('tokens',{}).get('access_token') or data.get('access_token',''))
else:
    print(raw.replace('Bearer ',''))
")

curl -s -H "Authorization: Bearer $TOKEN" "{REGISTRY_URL}/api/servers?limit=2000" > /tmp/servers.json
curl -s -H "Authorization: Bearer $TOKEN" "{REGISTRY_URL}/api/agents?limit=2000" > /tmp/agents.json
curl -s -H "Authorization: Bearer $TOKEN" "{REGISTRY_URL}/api/skills?limit=2000" > /tmp/skills.json

Read the full file on GitHub · 197 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. 10d ago First seen · 197 lines · 75 tokens per session scan A b8fc3196d7af

Subscribe to this mod's changes

search-benchmark is a skill published in the GitHub repository agentic-community/mcp-gateway-registry (903 stars, last pushed yesterday), licensed Apache-2.0. It adds 75 tokens to every session and 1,925 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

nft-standards

Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.

wshobson/agents · 48 tokens

postgresql-table-design

Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.

wshobson/agents · 37 tokens

parallel-feature-development

Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…

wshobson/agents · 105 tokens

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

istio-traffic-management

Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.

wshobson/agents · 40 tokens

event-store-design

Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.

wshobson/agents · 33 tokens