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 agentmods add instructions/insanetic/data-max/claude-mdgit clone --depth 1 https://github.com/insanetic/data-maxWhat 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 | $0.00859 | $0.00859 |
| Opus 5 | $0.00430 | $0.00430 |
| Sonnet 5 | $0.00172 | $0.00172 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
data-max CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repo is
This is a Claude Code plugin for working with data, published as a single-plugin marketplace — not an application. There is no build step, no test runner, and no runtime. "Shipping" means: edit a SKILL.md (or its supporting files), keep the manifests valid, commit, and push. Installers pull the result via /plugin marketplace add insanetic/data-max, then /plugin install data-max@data-max.
The marketplace name (in marketplace.json) and the plugin name (in plugin.json) are both data-max — so data-max@data-max (<plugin>@<marketplace>) is correct, not a typo. Skills are invoked as /data-max:<skill> (/<plugin>:<skill>).
Layout
.claude-plugin/marketplace.json ← the marketplace manifest; lists the one plugin (data-max)
.claude-plugin/plugin.json ← the data-max plugin manifest
skills/<skill>/SKILL.md ← the skill itself (auto-discovered, no path config needed)
skills/<skill>/references/ ← progressive-disclosure docs, loaded on demand
skills/<skill>/scripts/ ← executable helpers a skill may run (none yet)
One plugin (data-max) ships three skills that form a data lifecycle:
data-review— reviews a raw data file (CSV/TSV/JSON/XML/Excel) for warehouse readiness and produces a tiered cleansing report. Reviews only; never touches the data.data-transform— consumes adata-reviewreport and produces the cleaned, warehouse-ready CSV(s) via a rerunnable script undertools/.data-review→data-transformis a deliberate two-step pipeline (the report is the spec), not interchangeable.metric-creator— authors versioned, DSL-compatible metric (data cube) and dimension definitions as copy-pasteable JSON, driven by a DDL schema the user provides. Stands on its own.
The skill name is also what users type after /data-max: — e.g. /data-max:data-review. The data- prefix on the pair is deliberate: it keeps them in the same "data file / data model" context and avoids a bare review (which could read as reviewing a metric).
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.
- 2d ago First seen · 39 lines · 859 tokens per session scan A 057bc537d4a8
data-max CLAUDE.md is an instructions file published in the GitHub repository insanetic/data-max (2 stars, last pushed 3mo ago), licensed MIT. It adds 859 tokens to every session, about $0.0043 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.