benchmark

A benchmark command for evaluating the conversion of published Bankstatemently bank statements.

In plain words
What is it for?
Use it with a benchmark statement ID, PDF URL, or benchmark request to convert the statement and report extraction accuracy, integrity, overall score, and major failures.
Why use it?
It provides a structured way to check whether a converted statement was extracted accurately and kept its data intact.

Command

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 commands/bankstatemently/plugins/benchmark
Clone the repo
git clone --depth 1 https://github.com/bankstatemently/plugins
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 246 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 $0.00035 $0.00246
Opus 5 $0.00017 $0.00123
Sonnet 5 $0.00007 $0.00049
Haiku 4.5 $0.00003 $0.00025

Measured yesterday against content hash 414ed7d83bc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

benchmark 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 yesterday.

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.

bankstatemently/commands/benchmark.md · 27 lines

What it actually says

Input: $ARGUMENTS

Benchmark

Input: a benchmark statement id, PDF URL, or free-text benchmark request. Output: extraction accuracy, integrity score, overall score, and major failure categories, citing the benchmark statement id and converted document content_hash.

Treat the input as a benchmark statement id, PDF URL, or free-text benchmark request.

Follow this sequence:

  1. Read the benchmark catalog resource and choose the named published statement.
  2. Convert the benchmark PDF with convert_statement.
  3. Fetch the converted data with get_statement using original data mode.
  4. Pass the benchmark statement id and original parsed transactions to evaluate_benchmark.
  5. Present extraction accuracy, integrity score, overall score, and any major failure categories. Cite the benchmark statement id and converted document content_hash.

Example prompt: Convert and score the published bsb-004 benchmark statement.

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. yesterday First seen · 27 lines · 35 tokens per session scan A 414ed7d83bc6

Subscribe to this mod's changes

benchmark is a command published in the GitHub repository bankstatemently/plugins (1 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 246 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.