session-measurement

session-measurement is a skill for Claude Code from jovesun-lab/whetstone. It costs 188 tokens per session (2,820 once invoked), scanned A, original, MIT.

A session benchmark that records a small set of objective measures for an AI agent and compares them over time. A benchmark is a repeatable way to check whether performance improved or declined.

In plain words
What is it for?
Use it after agent sessions to count results, maintain a trend table, append measurements to a log, and optionally create a chart.
Why use it?
It helps separate real improvement from a change that only feels better after switching models, operating instructions, or skills.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: built for cline.

Part of the session-measurement plugin — 1 skill shipped together

Good fit Use it after agent sessions to count results, maintain a trend table, append measurements to a log, and optionally create a chart.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jovesun-lab/whetstone/session-measurement
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.

Any agent
npx skills add jovesun-lab/whetstone --skill session-measurement
Clone the repo
git clone --depth 1 https://github.com/jovesun-lab/whetstone

Made for: Claude Code.

Or install session-measurement, the plugin that ships this one along with the rest of its 1 skill.

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 session-measurement

README.md
[![agentmods](https://agentmods.dev/badge/skills/jovesun-lab/whetstone/session-measurement/github.svg)](https://agentmods.dev/skills/jovesun-lab/whetstone/session-measurement)
Your own site
<a href="https://agentmods.dev/skills/jovesun-lab/whetstone/session-measurement"><img src="https://agentmods.dev/badge/skills/jovesun-lab/whetstone/session-measurement/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 session-measurement

Your own site · 80×15
<a href="https://agentmods.dev/skills/jovesun-lab/whetstone/session-measurement"><img src="https://agentmods.dev/badge/skills/jovesun-lab/whetstone/session-measurement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 188 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,820 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 $0.00188 $0.02820
Opus 5 $0.00094 $0.01410
Sonnet 5 $0.00038 $0.00564
Haiku 4.5 $0.00019 $0.00282

Measured 8d ago against content hash 96b20ee607fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

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 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.

session-measurement/skills/session-measurement/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session measurement — agent performance benchmark

For any AI agent reading this file. The frontmatter uses Claude's skill format; the body is plain markdown. It works the same for Claude, OpenAI, Gemini, Cursor, Cline, Aider, or a local model — paste the body in as a prompt if your platform has no skill system. Assume nothing about your host's capabilities; everything here degrades gracefully.

You turn a finished agent session into a row of objective counts, record it in a running trend table, and append it to a persistent log. Do this every session and the trend tells you, over a long run, whether the agent is getting better or worse as its model / frame / skills change.

The canonical output is a plain-markdown trend table — no code execution, no dependencies, works for literally any agent (even one that can't run code). A polished chart image is an optional add-on for hosts that can render one; it's presentation, not the measurement. So the irreplaceable core of this skill is the metric frame + the counting disciplines + the data, not any particular renderer.

This skill is agent-agnostic and user-agnostic. The metric frame and the disciplines below work for any agent. Three things vary per project and live in a small config.json: where session transcripts come from, what counts as critical for this domain, and what the version axis means. On first use you set that config up (below), then every run reuses it.


The metric spine (keep these constant — comparability over time is the whole point)

Six counts per session. Green = a strength (higher is better); red = a weakness (higher is worse). Plus two per-session attributes (version, main-goal outcome).

Metric Color Counts
Redefinitions absorbed green times the task was redefined and the agent folded the change in without dropping earlier constraints
Clarifying gates raised green times the agent asked instead of guessing on a genuine ambiguity/conflict
Errors the agent self-caught green flaws the agent caught in its own output before the human did
Misses the human caught red factual/craft misses the human had to send back
Critical bugs — agent caught green severe defects (see below) the agent caught itself
Critical bugs — human caught red severe defects that slipped to the human

Read the full file on GitHub · 219 lines

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 · 219 lines · 188 tokens per session scan A 96b20ee607fa

Subscribe to this mod's changes

session-measurement is a skill published in the GitHub repository jovesun-lab/whetstone (8 stars, last pushed 18d ago), licensed MIT. It adds 188 tokens to every session and 2,820 once invoked, about $0.0009 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.