compare

compare is a skill for Claude Code from ai-analyst-lab/ai-analyst-plus. It costs 115 tokens per session (1,001 once invoked), scanned A, original, MIT.

A skill that compares an analytics question with and without a selected piece of context, such as a metric definition. It reports how the answers, citations, and stability change across repeated runs.

In plain words
What is it for?
Use it to compare an analyst’s responses for the same question with a setup directory present and absent, using a chosen number of runs.
Why use it?
It tests whether added context actually changes system behaviour instead of assuming that it helps. This can reveal whether a definition reduces inconsistent answers.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

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 skills/ai-analyst-lab/ai-analyst-plus/compare
Any agent
npx skills add ai-analyst-lab/ai-analyst-plus --skill compare
Clone the repo
git clone --depth 1 https://github.com/ai-analyst-lab/ai-analyst-plus

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 compare

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst-plus/compare.svg)](https://agentmods.dev/skills/ai-analyst-lab/ai-analyst-plus/compare)
Your own site
<a href="https://agentmods.dev/skills/ai-analyst-lab/ai-analyst-plus/compare"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst-plus/compare.svg" alt="Measured on agentmods" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,001 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 5.1 $0.00115 $0.01001
Opus 5 $0.00057 $0.00500
Sonnet 5 $0.00023 $0.00200
Haiku 4.5 $0.00012 $0.00100

Measured 6d ago against content hash 984e410e8763, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

compare 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 6d 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/skills/compare/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Compare (with and without)

Purpose

Measure what a piece of context is doing, instead of asserting it. Run the same question two ways, once without the context (for example, no metric definition) and once with it, and report the delta: did the spread collapse, did the runs start citing the definition, did the verdict go from drifts to stable. The setup whose presence collapses the drift is the context that moves the answer. Convergence is stability, not correctness.

Invocation

/compare "<the question>" --with <setup_dir> [N] Default N = 5. The setup is a directory of meaning-only definition overlays (for example the retention definition at .knowledge/comparisons/conditions/c1_retention_contract/). The baseline is the analyst with that setup absent.

Example: /compare "What's our retention rate?" --with .knowledge/comparisons/conditions/c1_retention_contract

How to run it

The math and the report live in the standalone eval tool (~/projects/ai-analytics-evals). The run step is the reliability skill. This skill is the glue: stage a setup, run reliability, repeat, compute the delta, restore. The user never types a command; you do each step.

Step 1 - baseline (without the context)

Make sure the baseline is active (the context absent). Use the eval tool's adapter to restore the base dictionary:

import sys; sys.path.insert(0, "<HOME>/projects/ai-analytics-evals")
from aievals.adapters.ai_analyst_plus import AIAnalystPlusAdapter
AIAnalystPlusAdapter().restore()

Then run the reliability check on the question (the /reliability skill: fire N independent sub-agents, each fresh context, each reporting headline / measured / definition_source). Save the N results to a run directory, for example .knowledge/comparisons/<question-slug>/<ts>-baseline/runs.json.

Step 2 - with the context

Stage the setup, then run the reliability check again into a second run directory:

AIAnalystPlusAdapter().stage("<the setup dir>")   # composes base + the definition overlay

Run reliability again into .../<ts>-with-context/runs.json.

Read the full file on GitHub · 79 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. 6d ago First seen · 79 lines · 0 tokens per session scan A 984e410e8763

Subscribe to this mod's changes

compare is a skill published in the GitHub repository ai-analyst-lab/ai-analyst-plus (19 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 1,001 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens