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 insanetic/data-max --skill metric-creatorgit clone --depth 1 https://github.com/insanetic/data-maxWrote 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/insanetic/data-max/metric-creator)<a href="https://agentmods.dev/skills/insanetic/data-max/metric-creator"><img src="https://agentmods.dev/badge/skills/insanetic/data-max/metric-creator.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00159 | $0.04937 |
| Opus 5 | $0.00079 | $0.02469 |
| Sonnet 5 | $0.00032 | $0.00987 |
| Haiku 4.5 | $0.00016 | $0.00494 |
Grade A, and why
metric-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metric Creator
Author and debug metrics (data cubes) and dimensions for a data source as copy-pasteable artifacts. The two outputs are:
- a metric file — a single data cube: a select expressed in the DSL JSON dialect
that returns exactly one number, aliased
value. Named and versioned, e.g.total_revenue.v1.0.json. dimensions.md— the source's reusable dimensions (how the metric is sliced and filtered), human-readable and copy-pasteable.
The DSL is a standalone representation, not SQL
The metric file is a declarative JSON DSL — a self-contained, structured
representation of a query, not SQL text. Its semantics are derived from and
resemble PostgreSQL, so leaning on what you know about PostgreSQL (how coalesce,
nullif, sum, division, casts behave) is a fine way to reason about a definition.
But treat that only as an aid to understanding: don't describe these artifacts as
"SQL", and don't frame the work as "generating SQL" — you are authoring DSL nodes
($project, $from, $where, $variadic, …) that the platform interprets itself.
What this is for
This skill extends a DSL-compatible Business Analytics platform — it authors the analytical data cubes (metrics) and dimensions that power the platform's analytics. It is not a general business-intelligence/reporting tool, not a dashboard builder, and not a query-builder for arbitrary databases: every artifact targets the platform's semantic layer and its runtime contract (below). If a request is really about generic BI, ad-hoc querying, or another platform, say so rather than forcing it into this shape.
Metrics are decision-critical: a wrong number is worse than a missing one. When you are not certain a definition is correct, research it, then ask — do not guess.
When to use
- The user wants a metric/KPI expressed as JSON (named or described).
- The user is working under
metrics/, or hands you a DDL/schema JSON. - The user wants to modify or debug an existing metric file or
dimensions.md(wrong value, double counting, missing filter, returns >1 row, etc.).
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/examples/hotel_data_source/avg_revenue_per_night.v1.0.json 1.7 KB
- references/examples/hotel_data_source/dimensions.md 2.8 KB
- references/examples/hotel_data_source/interaction_rate.v1.0.json 2.3 KB
- references/examples/hotel_data_source/total_revenue.v1.0.json 944 B
- references/expression-cookbook.md 17 KB
- references/semantic-layer-schema.json 17 KB
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.
- 7d ago First seen · 364 lines · 159 tokens per session scan A 177527ee4f10
metric-creator is a skill published in the GitHub repository insanetic/data-max (2 stars, last pushed 3mo ago), licensed MIT. It adds 159 tokens to every session and 4,937 once invoked, about $0.0008 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.
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…