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 skills/emcd/nb-mcp-server/notebook-hygienenpx skills add emcd/nb-mcp-server --skill notebook-hygienegit clone --depth 1 https://github.com/emcd/nb-mcp-serverWrote 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/emcd/nb-mcp-server/notebook-hygiene)<a href="https://agentmods.dev/skills/emcd/nb-mcp-server/notebook-hygiene"><img src="https://agentmods.dev/badge/skills/emcd/nb-mcp-server/notebook-hygiene.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 | $0.00044 | $0.01338 |
| Opus 5 | $0.00022 | $0.00669 |
| Sonnet 5 | $0.00009 | $0.00268 |
| Haiku 4.5 | $0.00004 | $0.00134 |
Grade A, and why
notebook-hygiene 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 5d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notebook Hygiene
Purpose
Restore a project notebook to a small, predictable working set without losing active work, durable rationale, or lifecycle-managed records. Treat cleanup as an information-architecture task, not a bulk deletion exercise.
Entry Conditions
- Identify one explicit target notebook. If the user did not name one, ask before continuing.
- Read the repository instructions and local notebook guidance first. Prefer
AGENTS.md, the root README, and files such asdocumentation/agents/notebook.mdwhen present. - Use the
nbMCP tools for notebook operations. Notebook selectors are not repository filesystem paths. - Do not inspect or modify other notebooks merely because the target notebook references them.
- If the user requested an audit or assessment, do not mutate anything. If the user explicitly requested cleanup, apply only unambiguous changes and present ambiguous cases together for a decision.
For a non-trivial cleanup, track the audit, classification, mutation, and verification phases with the session task-list tool.
Audit
Build the inventory before changing anything:
- List top-level folders and root-level items.
- List child folders and their contents. Follow the depth allowed by local policy; do not assume every notebook uses the same component names.
- Inventory open and completed todos. Confirm todo state from
[ ]and[x]rather than decorative item glyphs. - Inspect candidate stale records, including old handoffs, completed reviews, resolved issues, session notes, test notes, root-level notes, and duplicated trackers.
- Search for status tags, old selectors, references to completed trackers, and notes hidden at a category root alongside component subfolders.
- Read each candidate before classifying it. Titles and age alone are not enough evidence for deletion.
Classify each candidate into one of these groups:
| Class | Treatment |
|---|---|
| Active | Keep in the local issue-type/component taxonomy. |
| Lifecycle-managed | Leave in place and use its owning workflow or CLI. |
| Durable history | Move to artifacts/<component> or the local equivalent. |
| Procedure | Move to procedures/<component> or the local equivalent. |
| Completed | Delete when the outcome is preserved in code, tests, releases, or durable documentation. |
| Stale or duplicate | Delete after confirming that no unique action or rationale remains. |
| Ambiguous | Preserve and ask one bundled clarification question. |
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.
- 5d ago First seen · 137 lines · 44 tokens per session scan A 4c113d80b0d3
notebook-hygiene is a skill published in the GitHub repository emcd/nb-mcp-server (1 stars, last pushed 22d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,338 once invoked, about $0.0002 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.