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 agents/emcd/nb-mcp-server/notebookgit clone --depth 1 https://github.com/emcd/nb-mcp-serverWhat 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 | $0.00000 | $0.01248 |
| Opus 5 | $0.00000 | $0.00624 |
| Sonnet 5 | $0.00000 | $0.00250 |
| Haiku 4.5 | $0.00000 | $0.00125 |
Grade A, and why
notebook 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nb MCP Tools
The nb MCP server provides LLM-friendly access to the nb note-taking system with proper escaping and project-specific notebook context.
When to Use
- Project coordination: Record handoffs, document project policies and procedures, maintain task lists.
- Issue tracking: Create and manage todos with status tracking.
- Knowledge sharing: Document patterns, APIs, and project-specific knowledge.
- Meeting notes: Record discussions and action items.
Scope and Noise Control
- Prefer to update an existing related note/todo over creating a new one when context already exists.
- Avoid logging routine, immediately completed mechanical actions in separate notes.
- Create new notes/todos when information is likely to be useful across sessions or for other collaborators.
Tagging Conventions
Use consistent tags for discoverability:
- Project Component:
#component-<name>(e.g.,#component-data-models) - Task Type:
#task-<type>(e.g.,#task-design,#task-bug) - Status:
#status-<state>(e.g.,#status-in-progress,#status-review) - Coordination:
#handoff,#coordination - Assignment: Avoid owner tags (for example
#llm-*) for task ownership. Use lane/folder ownership and explicit owner text in the note body when needed.
Common Patterns
- Check for handoffs: use
searchwith#handoffand#status-reviewtags. - Find active component work: use
searchwith#component-<name>and#status-in-progresstags. - Track todos: use the
todo,tasks,do, andundotools. - Organize with folders: use
foldersandmkdir.
Choosing todo vs add
- Use the
todotool for any item with actionable state (open/done): todos, bugs, and issues. This gives the note a checkbox, enablesdo/undostate tracking, and makes it appear intasksoutput. - Use the
addtool for everything else: coordination notes, decisions, designs, ideas, reference material, handoffs, and meeting notes. - Always specify a
folderwhen creating a note. A note created without a folder lands at the notebook root and is invisible to folder-scoped list views. - Do not duplicate: if a bug or task is already tracked in
issues/<component>/ortodos/<component>/, do not also create a matching todo. Reference the existing selector in coordination notes or related todo bodies instead.
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 · 69 lines · 0 tokens per session scan A 7bd7b9158c3c
notebook is an agent published in the GitHub repository emcd/nb-mcp-server (1 stars, last pushed 18d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,248 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.
Other agents, from other repositories
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
chorus-task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn via the blocking subagent tool after chorussubmitforverify.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
analyst
Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…