A benchmark command for measuring how well qmd search finds expected files across four search methods.

Use it to compare keyword, vector, hybrid, and reranked search, test configuration changes, and catch search regressions.

It replaces guesswork with precision, recall, ranking, and F1 measurements on a known set of queries and answers.

bench — Command for Claude Code by ramonclaudio/skills

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/ramonclaudio/skills

Made for: Claude Code.

Or install qmd, the plugin that ships this one along with the rest of its 2 skills, 18 commands, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/ramonclaudio/skills/bench/github.svg)](https://agentmods.dev/commands/ramonclaudio/skills/bench)

Your own site

<a href="https://agentmods.dev/commands/ramonclaudio/skills/bench"><img src="https://agentmods.dev/badge/commands/ramonclaudio/skills/bench/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/ramonclaudio/skills/bench"><img src="https://agentmods.dev/badge/commands/ramonclaudio/skills/bench.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 313 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.

Model	Per session	Once invoked
Fable 5.1	$0.00024	$0.00313
Opus 5.5	$0.00010	$0.00125
Sonnet 5.5	$0.00005	$0.00063
Haiku 4.5	$0.00002	$0.00031

Measured 2mo ago against content hash 906a029cbce4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bench 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 2mo 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/qmd/commands/bench.md · 23 lines

What it actually says

Run qmd bench $ARGUMENTS. Compares 4 backends on the same labeled queries:

bm25: BM25 keyword only
vector: vector cosine only
hybrid: BM25 + vector RRF fusion (no LLM reranker)
full: full hybrid pipeline (with LLM reranker)

Reports precision@k, recall, MRR, and F1 per backend so you can quantify how much the reranker buys you over plain BM25 on the user's specific corpus.

Flags:

--json: machine-readable output instead of the human table
-c <name>: override the fixture's collection field

Fixture format is {description, version, collection?, queries: [{id, query, type, description, expected_files, expected_in_top_k}]}. Each query has a type (exact|semantic|topical|cross-domain|alias) for grouping in the report and expected_files (paths relative to the collection) for scoring. Upstream ships an example at src/bench/fixtures/example.json.

Use this for A/B-testing config changes (--candidate-limit, --chunk-strategy, model overrides) and for catching regressions after qmd update.

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.

2mo ago First seen · 23 lines · 24 tokens per session scan A 906a029cbce4

Subscribe to this mod's changes

bench is a command published in the GitHub repository ramonclaudio/skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 313 once invoked, about $0.0001 per session on Opus 5.5. 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.

Analytics and metrics Research

bench next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
benchramonclaudio/skills	Command	4	5mo ago	MIT	A	24	Claude Code
checklistgithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	yesterday	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	yesterday	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	yesterday	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	yesterday	MIT	A	14	Claude Code