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 ngerakines/jd --skill jd-system-setupgit clone --depth 1 https://github.com/ngerakines/jdWrote 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/ngerakines/jd/jd-system-setup)<a href="https://agentmods.dev/skills/ngerakines/jd/jd-system-setup"><img src="https://agentmods.dev/badge/skills/ngerakines/jd/jd-system-setup.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 | $0.00108 | $0.01660 |
| Opus 5 | $0.00054 | $0.00830 |
| Sonnet 5 | $0.00022 | $0.00332 |
| Haiku 4.5 | $0.00011 | $0.00166 |
Grade A, and why
jd-system-setup 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Johnny.Decimal System Setup
This skill creates a new Johnny.Decimal system from scratch — building the folder structure, standard zeros, and initial JDex based on the user's needs.
1. Gather Requirements
Before creating anything, understand what the user needs.
1.1 Single or Multi-System?
Ask the user:
- Single system: One organizational domain (e.g., just personal life, or
just work). No system prefix needed — folders use plain
AC.IDnotation. - Multi-system: Multiple distinct domains (e.g., personal + work, or
personal + work + child). Each system gets a
SYSprefix using the[A-Z][0-9][0-9]format.
If the user already has JD systems, check the existing root to avoid conflicts.
1.2 System Identity
For each system to create, gather:
- System code (multi-system only): A three-character
[A-Z][0-9][0-9]identifier. Encourage memorable codes (e.g.,P10for personal,W20for work). The code should be visually distinctive. - System name: A plain-English name (e.g., "Personal", "Work", "Jamie").
- Root location: Where the system will live on disk. Common locations:
~/Library/Mobile Documents/com~apple~CloudDocs/JD/(iCloud Drive)~/Documents/JD/~/JD/
1.3 Areas and Categories
Walk the user through defining their areas. Provide guidance:
- Maximum 10 areas (including
00-09 System) - Each area covers a major life/work domain
- Fewer areas is better — compression over granularity
- Area
00-09is always created automatically for system management
For each area, ask about categories:
- Maximum 10 categories per area
- Categories are "where you work" — collections of similar things
- Category names should be short and clear
For each category, ask if they have specific IDs in mind, or if they'll create IDs as content arrives.
2. Create the Folder Structure
2.1 System Root
Create the system root folder:
- Single system:
[Root]/(e.g.,~/JD/) - Multi-system:
[Root]/SYS Name/(e.g.,~/JD/P10 Personal/)
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 · 266 lines · 108 tokens per session scan A 66e3baf8fa1b
jd-system-setup is a skill published in the GitHub repository ngerakines/jd (7 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 108 tokens to every session and 1,660 once invoked, about $0.0005 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.