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 commands/data-wise/craft/hubgit clone --depth 1 https://github.com/Data-Wise/craftWhat 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 | $0.00008 | $0.07764 |
| Opus 5 | $0.00004 | $0.03882 |
| Sonnet 5 | $0.00002 | $0.01553 |
| Haiku 4.5 | $0.00001 | $0.00776 |
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.
How it starts
The opening of the file, as written. The whole thing — 784 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 0: Load Command Data (Auto-Detection)
IMPORTANT: Before displaying the hub, load command data from the discovery engine:
import sys
from pathlib import Path
# Add commands directory to path
plugin_dir = Path.cwd()
sys.path.insert(0, str(plugin_dir))
# Import discovery engine
from commands._discovery import get_command_stats, load_cached_commands
# Get current command statistics
stats = get_command_stats()
commands = load_cached_commands()
# Available data:
# - stats['total']: Total command count (e.g., 47)
# - stats['categories']: Dict of category counts (e.g., {'code': 13, 'ci': 8, ...})
# - stats['with_modes']: Commands supporting modes
# - stats['with_dry_run']: Commands with dry-run support
# - commands: Full list of command objects with metadata
# Count skills, agents, and tests for banner
from pathlib import Path
skill_count = len(list((plugin_dir / 'skills').rglob('SKILL.md'))) if (plugin_dir / 'skills').exists() else 0
agent_count = len(list((plugin_dir / 'agents').glob('*.md'))) if (plugin_dir / 'agents').exists() else 0
# Read test count from CLAUDE.md or .STATUS (extract number from "N tests passing")
import re
test_count = "?"
for source in [plugin_dir / 'CLAUDE.md', plugin_dir / '.STATUS']:
if source.exists():
content = source.read_text()
m = re.search(r'(\d+)\s+tests?\s+pass', content)
if m:
test_count = m.group(1)
break
Use this data to populate the hub display below with accurate, auto-detected counts.
Step 1: Detect Project Context
Detection Rules (check in order):
1. .claude-plugin/plugin.json → Claude Code Plugin
2. DESCRIPTION file → R Package
3. pyproject.toml → Python Package
4. package.json → Node.js Project
5. _quarto.yml → Quarto Project
6. mkdocs.yml → MkDocs Project
7. Otherwise → Generic Project
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.
- yesterday First seen · 784 lines · 8 tokens per session scan A 020d429ac823
hub is a command published in the GitHub repository Data-Wise/craft (4 stars, last pushed 16d ago), licensed MIT. It adds 8 tokens to every session and 7,764 once invoked, about $0.0000 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 commands, from other repositories
readme-audit
Audit a README's reading flow by treating it as a conversion funnel. Every section is evaluated against a target reader and a terminal action. Produces a structured audit blueprint that feeds directly into /readme-restructure.
readme-restructure
Execute a /readme-audit blueprint. Rewrites the README to the evaluator → conversion → links structure and creates linked docs by extracting and reorganising existing content.
build-fix
Fix build and type failures with minimal diffs.
checkpoint
Record a verified checkpoint before the next phase.
doctor
Check the install surface for missing files and invalid manifests.
feature-dev
Drive a feature from plan to implementation to review.