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.
npx skills add ai-analyst-lab/ai-analyst-plugin --skill always-comparegit clone --depth 1 https://github.com/ai-analyst-lab/ai-analyst-pluginWrote 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.
[](https://agentmods.dev/skills/ai-analyst-lab/ai-analyst-plugin/always-compare)<a href="https://agentmods.dev/skills/ai-analyst-lab/ai-analyst-plugin/always-compare"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst-plugin/always-compare.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00112 | $0.01493 |
| Opus 5 | $0.00056 | $0.00746 |
| Sonnet 5 | $0.00022 | $0.00299 |
| Haiku 4.5 | $0.00011 | $0.00149 |
Grade A, and why
always-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 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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Always Compare
Purpose
A number alone is not an insight. "Conversion rate is 3.2%" tells the reader nothing actionable — they cannot tell if that is a crisis or a record high. This skill enforces one rule: every metric ships with a comparison.
When to Use
Before presenting ANY number to the user — in chat, in a report, in a chart caption,
in a Slack message, or on a slide. This runs on every analysis output, alongside
question-framing (which runs at the start; this one runs at the end).
The Rule
Never show a number alone. Anchor it to at least one comparison.
Pick the comparison that best serves the decision. In priority order:
| # | Comparison Type | Use When | Example |
|---|---|---|---|
| 1 | vs. prior period | The question is "is this changing?" | "down from 4.1% last month" |
| 2 | vs. benchmark / average | The question is "is this normal?" | "below the 3.8% site-wide average" |
| 3 | vs. another segment | The question is "who is affected?" | "vs. 5.4% on desktop" |
Two comparisons beat one. A prior-period delta plus a benchmark tells the reader both the direction and the altitude. Use both when you have both.
Instructions
Step 1: Find every number in your draft output
Scan the response you are about to send. Every figure — headline stats, table cells, chart annotations, sentences in the narrative — is in scope.
Step 2: Attach a comparison to each one
For each metric, ask: compared to what? Then pull the comparison from the data:
- Prior period: same metric, previous week / month / quarter (match the grain of the metric)
- Benchmark: site-wide average, cohort average, target, or historical baseline
- Segment: the same metric for a contrasting slice (mobile vs. desktop, new vs. returning, channel A vs. B)
Compute the comparison in the same query where practical — it is cheaper and less error-prone than a second round trip, and it guarantees the filters match.
Step 3: State the delta, not just both numbers
Do the subtraction for the reader. "3.2%, down from 4.1%" is better than "3.2% (last month: 4.1%)". Give direction (up/down) and magnitude (absolute points or relative %) — and be explicit about which you are using: "down 0.9pp (a 22% relative decline)".
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.
- 8d ago First seen · 101 lines · 112 tokens per session scan A e6073d07e1a8
always-compare is a skill published in the GitHub repository ai-analyst-lab/ai-analyst-plugin (32 stars, last pushed 11d ago), licensed MIT. It adds 112 tokens to every session and 1,493 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…