Plumbline: Command for Claude Code

.claude/commands/bench-watch.md

bench-watch is a command for Claude Code from DYAI2025/Plumbline. It costs 54 tokens per session (667 once invoked), scanned A, original, no licence file.

A command for running part of a Plumbline benchmark, a test used to measure how well a system performs. It waits for the run to finish and produces a standard summary for each model.

In plain words
What is it for?
Launching or joining a benchmark slice, waiting for completion, and reviewing catch-rate and false-alarm results for each model.
Why use it?
It removes the need to repeatedly start a benchmark, check its status, and assemble the results by hand.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is DYAI2025/Plumbline's own configuration. It tells Claude Code how to work on Plumbline itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Plumbline configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DYAI2025/Plumbline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/DYAI2025/Plumbline/main/.claude/commands/bench-watch.md
Clone the repo
git clone --depth 1 https://github.com/DYAI2025/Plumbline

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 bench-watch

README.md
[![agentmods](https://agentmods.dev/badge/commands/dyai2025/plumbline/bench-watch.svg)](https://agentmods.dev/commands/dyai2025/plumbline/bench-watch)
Your own site
<a href="https://agentmods.dev/commands/dyai2025/plumbline/bench-watch"><img src="https://agentmods.dev/badge/commands/dyai2025/plumbline/bench-watch.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 667 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 unknown 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 $0.00054 $0.00667
Opus 5 $0.00027 $0.00333
Sonnet 5 $0.00011 $0.00133
Haiku 4.5 $0.00005 $0.00067

Measured 8d ago against content hash 4d1cdcf94139, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

bench-watch 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.

.claude/commands/bench-watch.md · 43 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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 · 43 lines · 54 tokens per session scan A 4d1cdcf94139

Subscribe to this mod's changes

bench-watch is a command published in the GitHub repository DYAI2025/Plumbline (6 stars, last pushed 5d ago), with no licence file. It adds 54 tokens to every session and 667 once invoked, about $0.0003 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.