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 qkitzero/kage-bunshin --skill notebookgit clone --depth 1 https://github.com/qkitzero/kage-bunshinWrote 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/qkitzero/kage-bunshin/notebook)<a href="https://agentmods.dev/skills/qkitzero/kage-bunshin/notebook"><img src="https://agentmods.dev/badge/skills/qkitzero/kage-bunshin/notebook/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/qkitzero/kage-bunshin/notebook"><img src="https://agentmods.dev/badge/skills/qkitzero/kage-bunshin/notebook.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 | $0.00045 | $0.00630 |
| Opus 5.5 | $0.00018 | $0.00252 |
| Sonnet 5.5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
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 1mo 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notebook Skill
A workflow for performing search, browse, organize, and stats operations on the Notebook.
Prerequisites
First check the NOTEBOOK_PATH environment variable.
If not set:
Notebook is not configured.
Setup instructions:
1. Create a git repository for your Notebook
2. Add the following to .claude/settings.local.json:
{
"env": {
"NOTEBOOK_PATH": "/path/to/your/notebook-repo"
},
"permissions": {
"additionalDirectories": ["/path/to/your/notebook-repo"]
}
}
3. Restart Claude Code
Display this and exit. The following workflow only executes when Notebook is configured.
Workflow
Step 1: Determine the Operation
Classify the user's request into one of these operations:
| Operation | Trigger Examples |
|---|---|
| search | "find...", "any records about...?", "anything saved about...?" |
| browse | "show recent records", "list entries", "what's in the Notebook?" |
| organize | "organize tags", "update cross-references", "add related links" |
| stats | "Notebook statistics", "how much is stored?", "show breakdown" |
Step 2: Execute the Operation
Operate directly on the $NOTEBOOK_PATH path using the following tools.
search
- Glob for filename matching
- Grep frontmatter tags, title, type for matching
- Grep body for keyword matching
Output results in this format:
- File path, title, type, date
- Relevant snippet (2 lines before/after the match)
browse
- Glob to retrieve all entries
- Read frontmatter of each file
- Group by type, sort by date descending
organize
- Read target entries
- Edit frontmatter tags / related fields
- Update index.md (table format with date, title, type, path)
Confirm changes with the user before making modifications.
stats
- Glob to count all entries
- Grep to aggregate by type and project
- Aggregate tag frequency
Step 3: Format and Output Results
Format operation results for easy reading and present to the user.
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.
- 1mo ago First seen · 99 lines · 45 tokens per session scan A 4a65c119df8b
notebook is a skill published in the GitHub repository qkitzero/kage-bunshin (0 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 630 once invoked, about $0.0002 per session on Opus 5.5. 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
handoff
Create a structured session handoff when context is running low or work is pausing. Deep context mining, self-validation, multi-file splitting. Captures everything the next session needs.
mnemo
A file-based memory system for saving conversations, tool activity, and handoff notes between coding sessions. It keeps project memory separate from Claude’s built-in personal memory.
project-gotchas
A project memory system that records recurring mistakes and successful patterns in shared notes for coding tools. It keeps separate global notes and project-specific notes.
update
Integrate external info (research, status changes, reference material, deliverables) into the ops repo's knowledge base. Drop files in .update/ or pass content inline.
harden-memories
Audit the bd remember store and recommend which entries to prune, so each one earns its per-session bd prime injection cost. Read-only: it proposes a triage table plus the exact bd forget / migration commands; you run them. Use when bd remember entries have accumulated, feel stale, redundant, or conflicting, or when…
self-improvement
Turn friction you just hit into a concrete change to the workflow, so the same problem doesn't recur.