session-measurement

A measurement tool for tracking an AI agent’s performance across sessions using a small, consistent set of metrics. A session is one run of the agent, and a trend shows how results change over time.

In plain words
What is it for?
Benchmarking, scoring, grading, and comparing agent runs, including A/B tests. It records results in a plain Markdown table and can optionally render charts.
Why use it?
It helps determine whether a model, instruction setup, or skill change improved the agent or caused a regression.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add jovesun-lab/whetstone
agentmods
npx agentmods add plugins/jovesun-lab/whetstone/session-measurement
Clone the repo
git clone --depth 1 https://github.com/jovesun-lab/whetstone

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

session-measurement 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 2d 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.

session-measurement/.claude-plugin/plugin.json · 20 lines

What it actually says

{
  "name": "session-measurement",
  "description": "Measure an AI agent's per-session performance on a small, stable metric set and track it as a trend over a long run, so you can tell whether a change — a new model version, a new operating frame, a new skill set — actually improved the agent or regressed it. Records a plain-markdown trend table (canonical, zero-dependency); an optional script renders charts. Reach for it to benchmark, score, grade, or A/B an agent across sessions.",
  "version": "0.1.1",
  "author": {
    "name": "arcgram.io"
  },
  "homepage": "https://github.com/jovesun-lab/whetstone/tree/main/session-measurement",
  "repository": "https://github.com/jovesun-lab/whetstone",
  "license": "MIT",
  "keywords": [
    "agent-benchmark",
    "performance-trend",
    "session-measurement",
    "ai-agents",
    "regression-tracking",
    "evaluation"
  ]
}
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. 2d ago First seen · 20 lines scan A b6947a4dbd34

Subscribe to this mod's changes

session-measurement is a plugin published in the GitHub repository jovesun-lab/whetstone (8 stars, last pushed 12d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.