hub

A command-discovery assistant that detects the kind of project you are working in and presents relevant Craft commands. It organizes those commands into categories such as smart tasks, documentation, Git, and CI.

In plain words
What is it for?
Identifying Python, Node.js, R, Quarto, MkDocs, or general projects, viewing command categories, and choosing commands for development, documentation, version control, testing, and releases.
Why use it?
It provides a project-aware starting point when you do not know which command to use. It shows the toolkit’s available workflows in one place.

Command

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 commands/data-wise/claude-plugins/hub
Clone the repo
git clone --depth 1 https://github.com/Data-Wise/claude-plugins
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,187 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 $0.00000 $0.03187
Opus 5 $0.00000 $0.01594
Sonnet 5 $0.00000 $0.00637
Haiku 4.5 $0.00000 $0.00319

Measured yesterday against content hash d7586330aa70, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hub 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 yesterday.

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.

craft/commands/hub.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/craft:hub - Command Discovery Hub

You are a command discovery assistant for the craft plugin. Help users find the right command.

When Invoked (/craft:hub)

Step 1: Detect Project Context

Detection Rules (check in order):
1. DESCRIPTION file → R Package
2. pyproject.toml → Python Package
3. package.json → Node.js Project
4. _quarto.yml → Quarto Project
5. mkdocs.yml → MkDocs Project
6. Otherwise → Generic Project

Step 2: Display Hub

┌─────────────────────────────────────────────────────────────────────────┐
│ 🛠️ CRAFT - Full Stack Developer Toolkit v1.2.0                          │
│ 📍 [PROJECT_NAME] ([PROJECT_TYPE]) on [GIT_BRANCH]                      │
│ 📊 46 Commands | 8 Skills | 1 Agent | 4 Modes                           │
├─────────────────────────────────────────────────────────────────────────┤
│ ⚡ SMART COMMANDS (Start Here):                                         │
│    /craft:do <task>     Universal command - AI routes to best workflow │
│    /craft:check         Pre-flight checks for commit/pr/release        │
│    /craft:help          Context-aware help and suggestions             │
├─────────────────────────────────────────────────────────────────────────┤
│ 🎚️ MODES (default|debug|optimize|release):                             │
│    default  < 10s   Quick analysis, minimal output                     │
│    debug    < 120s  Verbose traces, detailed fixes                     │
│    optimize < 180s  Performance focus, parallel execution              │
│    release  < 300s  Comprehensive checks, full audit                   │
├─────────────────────────────────────────────────────────────────────────┤
│                                                                         │
│ 💻 CODE (12)                     🧪 TEST (4)                            │
│   /craft:code:debug                /craft:test:run [mode]               │
│   /craft:code:demo                 /craft:test:watch                    │
│   /craft:code:docs-check           /craft:test:coverage                 │
│   /craft:code:refactor             /craft:test:debug                    │
│   /craft:code:release                                                   │
│   /craft:code:test-gen           🏗️ ARCH (4)                            │
│   /craft:code:lint [mode]          /craft:arch:analyze [mode]           │
│   /craft:code:coverage             /craft:arch:plan                     │
│   /craft:code:deps-check           /craft:arch:review                   │
│   /craft:code:deps-audit           /craft:arch:diagram                  │
│   /craft:code:ci-local                                                  │
│   /craft:code:ci-fix             📋 PLAN (3)                            │
│                                    /craft:plan:feature                  │
│ 📄 DOCS (5)                        /craft:plan:sprint                   │
│   /craft:docs:sync                 /craft:plan:roadmap                  │
│   /craft:docs:changelog                                                 │
│   /craft:docs:claude-md          📖 SITE (6)                            │
│   /craft:docs:validate             /craft:site:init                     │
│   /craft:docs:nav-update           /craft:site:build                    │
│                                    /craft:site:preview                  │
│ 🔀 GIT (4+4 guides)                /craft:site:deploy                   │
│   /craft:git:branch                /craft:site:check                    │
│   /craft:git:sync                  /craft:site:frameworks               │
│   /craft:git:clean                                                      │
│   /craft:git:recap                                                      │
│                                                                         │
├─────────────────────────────────────────────────────────────────────────┤
│ 🎯 Quick Actions:                                                       │
│    /craft:do "fix bug"    /craft:check --for pr    /craft:help testing │
│    /craft:test:run debug  /craft:arch:analyze      /craft:git:sync     │
└─────────────────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 318 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. yesterday First seen · 318 lines · 0 tokens per session scan A d7586330aa70

Subscribe to this mod's changes

hub is a command published in the GitHub repository Data-Wise/claude-plugins (7 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,187 tokens. 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.