evaluate-retrieval

evaluate-retrieval is a skill for Claude Code, Codex from hyh0620/mcp-knowledge-service. It costs 18 tokens per session (175 once invoked), scanned A, original, MIT.

A measured test of document search for a named collection using example questions with known correct sources. Retrieval means finding the most relevant stored documents for a query.

In plain words
What is it for?
Use it to record returned sources, correct-source rank, citations, and response time, then calculate Hit@1, Hit@3, MRR, and citation matches.
Why use it?
It shows how often the search returns the right source and where it ranks, instead of relying on a subjective assessment of answer quality.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/query.py --query "health check" --collection <COLLECTION> --top-k 1.

Good fit Use it to record returned sources, correct-source rank, citations, and response time, then calculate Hit@1, Hit@3, MRR, and citation matches.

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/hyh0620/mcp-knowledge-service
agentmods
npx agentmods add skills/hyh0620/mcp-knowledge-service/evaluate-retrieval

Made for: Claude Code, Codex.

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 evaluate-retrieval

README.md
[![agentmods](https://agentmods.dev/badge/skills/hyh0620/mcp-knowledge-service/evaluate-retrieval/github.svg)](https://agentmods.dev/skills/hyh0620/mcp-knowledge-service/evaluate-retrieval)
Your own site
<a href="https://agentmods.dev/skills/hyh0620/mcp-knowledge-service/evaluate-retrieval"><img src="https://agentmods.dev/badge/skills/hyh0620/mcp-knowledge-service/evaluate-retrieval/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 evaluate-retrieval

Your own site · 80×15
<a href="https://agentmods.dev/skills/hyh0620/mcp-knowledge-service/evaluate-retrieval"><img src="https://agentmods.dev/badge/skills/hyh0620/mcp-knowledge-service/evaluate-retrieval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 175 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 $0.00018 $0.00175
Opus 5 $0.00009 $0.00088
Sonnet 5 $0.00004 $0.00035
Haiku 4.5 $0.00002 $0.00017

Measured 8d ago against content hash 0f92a54f51e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

evaluate-retrieval 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 8d 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.

.github/skills/evaluate-retrieval/SKILL.md · 35 lines

What it actually says

Evaluate Retrieval

Inputs

  • Collection name.
  • Golden test set with query and expected source.

Pipeline

  1. Confirm collection exists:
    python scripts/query.py --query "health check" --collection <COLLECTION> --top-k 1
    
  2. Run retrieval cases using the project evaluation script or a small client script.
  3. For each case record:
    • returned sources
    • first relevant rank
    • citation count
    • latency
  4. Compute:
    • Hit@1
    • Hit@3
    • MRR
    • citation expected-source match

Rules

  • Report numerator and denominator.
  • Do not use LLM subjective scoring as retrieval accuracy.
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. 8d ago First seen · 35 lines · 18 tokens per session scan A 0f92a54f51e7

Subscribe to this mod's changes

evaluate-retrieval is a skill published in the GitHub repository hyh0620/mcp-knowledge-service (0 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 175 once invoked, about $0.0001 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 2026-09-01.

Related

Other skills, from other repositories

vector-hybrid-search

Retrieve knowledge from a vector-store collection via the vector-mcp MCP server's vectorsearch tool — semantic (ANN) search, lexical BM25 search, or a hybrid of the two fused with Reciprocal Rank Fusion. Use when the agent must answer a question from an indexed corpus, pull top-k relevant chunks for RAG context, or…

Knuckles-Team/vector-mcp · 113 tokens

using-agent-brain

Expert Agent Brain skill for document search with BM25 keyword, semantic vector, hybrid, graph, and multi retrieval modes. Use when asked to "search documentation", "query domain", "find in docs", "bm25 search", "hybrid search", "semantic search", "graph search", "multi search", "find dependencies", "code…

SpillwaveSolutions/agent-brain · 249 tokens

vector-backend-operations

Select and connect the right vector-store backend for the vector-mcp MCP server — chromadb, postgres/pgvector, qdrant, couchbase, or mongodb — and supply the correct dbtype/connection parameters that every collection and search call needs. Use when the agent must decide which engine to target, wire up…

Knuckles-Team/vector-mcp · 113 tokens

vector-collection-management

Create, populate, list, and delete vector-store collections through the vector-mcp MCP server's vectorcollectionmanagement tool. Use when the agent must stand up a new RAG collection, ingest documents (from a directory, file paths/URLs, or raw text) into an existing collection, enumerate collections, or drop one …

Knuckles-Team/vector-mcp · 123 tokens

eval-set

Build and run a project-specific retrieval eval so changes to your rules or base prompt are scored, not eyeballed. Mirrors tests/groundtruth.json + clawness eval: you write prompt→expected-rule cases, then measure MRR@k and hit-rate before and after an edit. Run it after trimming a base prompt into ranked retrieval…

fullymiddleaged/Clawness · 98 tokens

Hybrid Search Architect

Designs a hybrid retrieval pipeline combining dense vector search and BM25 sparse search with reciprocal rank fusion, and explains when to use each configuration.

Notysoty/openagentskills · 32 tokens