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/drobins25/craft/craft-notebookgit clone --depth 1 https://github.com/drobins25/craftWrote 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/commands/drobins25/craft/craft-notebook)<a href="https://agentmods.dev/commands/drobins25/craft/craft-notebook"><img src="https://agentmods.dev/badge/commands/drobins25/craft/craft-notebook.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 | $0.00057 | $0.05602 |
| Opus 5 | $0.00028 | $0.02801 |
| Sonnet 5 | $0.00011 | $0.01120 |
| Haiku 4.5 | $0.00006 | $0.00560 |
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 4d 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 — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notebook
Low-ceremony capture for ideas and todos. The upstream of craft's compounding system.
Project Root
Set PROJECT to ${CRAFT_PROJECT_ROOT:-.}. All .craft/ paths resolve under this root.
Step 0: Route on First Argument
Inspect the first token of $ARGUMENTS. Route as follows:
| First token | Action |
|---|---|
| (empty) | Go to Step 1: List View |
idea |
Go to Step 2: Capture Flow with TYPE=idea |
todo |
Go to Step 2: Capture Flow with TYPE=todo |
note |
Go to Step 2: Capture Flow with TYPE=note |
| Anything else that looks like prose (no recognized subcommand) | Go to Step 3: Disambiguate Idea-or-Todo |
graduate / done / unknown single-token verbs |
Output hint, return |
Hint output for graduate, done, or unrecognized first-token verbs:
Print exactly:
I handle that conversationally - try saying "turn the X idea into a story" or "mark X done" and I'll do it.
Return without taking any other action. Do not run any helper. Do not show an AskUserQuestion. AC21 prohibits lifecycle action from typed subcommands. The example phrasings are the discoverability surface for users who hit this path - terser hints lose the educational moment.
Step 1: List View
Run the list helper and read its structured output:
bash ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/notebook-list.sh
The helper emits key=value records, one per entry, separated by blank lines, with fields TYPE, N, FILE, DATE, SLUG, TAGS, PREVIEW.
If output is empty: Print exactly:
Notebook empty.
Add an idea: /craft:notebook idea "your idea"
Add a todo: /craft:notebook todo "your todo"
Add a note: /craft:notebook note "a durable project fact"
Do NOT fire any AskUserQuestion (AC12). Return.
If output has entries: Parse the records and render three groups:
Ideas
[1] {DATE} {SLUG} {tags-section}
{PREVIEW}
[2] {DATE} {SLUG} {tags-section}
{PREVIEW}
Todos
[1] {DATE} {SLUG} {tags-section}
{PREVIEW}
Notes
[1] {DATE} {SLUG} {tags-section}
{PREVIEW}
Commands: idea "text" / todo "text" / note "text"
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.
- 4d ago First seen · 453 lines · 57 tokens per session scan A 36b035cb5f01
notebook is a command published in the GitHub repository drobins25/craft (53 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 5,602 once invoked, about $0.0003 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 2026-08-30.
Other commands, from other repositories
claudehut-learning-report
Show the ClaudeHut learning scoreboard — measured memory health (store size, reinforcement, effectiveness/recurrence, quality) so you can tell whether the agent is actually getting smarter across sessions. One-shot, read-only.
ingest
Ingest source material into an active wiki. Accepts URLs, file paths, PDFs, freeform text, or processes the inbox. Supports tweets via Grok MCP.
session
Capture, list, rehydrate, and promote llm-wiki session context. Supports automated hook capture into HUB/.sessions plus explicit promotion into topic raw notes.
al-context-create
Generate or update context.md file documenting project structure, architecture, and key patterns for AI assistants and developers. Use when you need to create project context documentation or update the context file.
memory-list
DEPRECATED: Use Serena listmemories instead. Lists recent memories from Forgetful with optional project filtering.
hf.memory
Scan the current conversation for architectural decisions, bug root causes, configuration choices, codebase patterns, and workflow preferences. Write each as a memory item to the local JSONL store for ingestion by the memory sync worker.