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-next-actiongit 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-next-action)<a href="https://agentmods.dev/skills/ngerakines/jd/jd-next-action"><img src="https://agentmods.dev/badge/skills/ngerakines/jd/jd-next-action/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ngerakines/jd/jd-next-action"><img src="https://agentmods.dev/badge/skills/ngerakines/jd/jd-next-action.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00150 | $0.04147 |
| Opus 5 | $0.00075 | $0.02073 |
| Sonnet 5 | $0.00030 | $0.00829 |
| Haiku 4.5 | $0.00015 | $0.00415 |
Grade A, and why
jd-next-action 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 10d 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 — 513 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Johnny.Decimal Next Action Dashboard
This skill creates a unified, prioritized view of everything requiring attention
across all Johnny.Decimal systems. It combines active tasks (from todo.txt),
unprocessed inbox items, and items needing review into a single report ordered
from most urgent to least urgent, followed by a "coming up" section for items
approaching actionability.
This skill is read-only — it never modifies any files. It reads and reports.
For task parsing rules, read ../jd-task-manager/references/jdtodo-spec.md
(the jdtodo.txt format specification).
1. Orientation: Discover the JD Environment
Before generating the report, build a mental map of the user's JD setup.
1.1 Locate the JD Root
The JD root folder is wherever the user's systems live. Common locations:
~/Library/Mobile Documents/com~apple~CloudDocs/JD/(iCloud Drive)~/Documents/JD/~/JD/- A project-specific folder the user designates
If you don't know the root, ask the user. If the user says "what should I do next" without further context, check the most common locations above. If you find exactly one, use it. If you find multiple or none, ask.
1.2 Identify Systems
List the top-level folders under the JD root. Each folder whose name matches
the pattern [A-Z][0-9][0-9] * is a JD system (e.g., P10 Personal,
W20 Work).
If the user has a single system (no SYS prefix), treat the entire JD root as one system.
If the user specified a system code as an argument (e.g., "next actions for P10"), limit scanning to that system only.
1.3 Load Each System's JDex
For every system you'll scan, read the JDex file at:
SYS/00-09 */00 */00.00 *JDex*
The JDex is needed to enrich task displays with human-readable descriptions
for +AC.ID references. If the JDex is missing, you can still generate the
report but cannot enrich JD codes — note this in the summary.
2. Scan Data Sources
For each system, locate and read these data sources. If a source doesn't exist, skip it and note the absence.
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.
- 10d ago First seen · 513 lines · 150 tokens per session scan A b48cee52cb87
jd-next-action is a skill published in the GitHub repository ngerakines/jd (7 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 150 tokens to every session and 4,147 once invoked, about $0.0007 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…
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.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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.