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.
git clone --depth 1 https://github.com/xiaojiou176-open/notebooklabWrote 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/plugins/xiaojiou176-open/notebooklab/provenote-outcome-bundle)<a href="https://agentmods.dev/plugins/xiaojiou176-open/notebooklab/provenote-outcome-bundle"><img src="https://agentmods.dev/badge/plugins/xiaojiou176-open/notebooklab/provenote-outcome-bundle/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/plugins/xiaojiou176-open/notebooklab/provenote-outcome-bundle"><img src="https://agentmods.dev/badge/plugins/xiaojiou176-open/notebooklab/provenote-outcome-bundle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
Notebooklab Claude Outcome Bundle 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.
What it actually says
{
"id": "notebooklab-claude-outcome-bundle",
"name": "Notebooklab Claude Outcome Bundle",
"version": "1.8.5",
"description": "Public-ready Claude Code starter bundle for Notebooklab MCP outcome workflows.",
"author": {
"name": "Notebooklab maintainers",
"url": "https://github.com/xiaojiou176-open/notebooklab"
},
"homepage": "https://github.com/xiaojiou176-open/notebooklab/blob/main/examples/hosts/claude-code/notebooklab-outcome-bundle/README.md",
"repository": "https://github.com/xiaojiou176-open/notebooklab",
"license": "MIT",
"keywords": [
"claude-code",
"mcp",
"notebooklab",
"drafts",
"research-threads"
]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 38 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 21 lines scan A ecfeeca88efc
Notebooklab Claude Outcome Bundle is a plugin published in the GitHub repository xiaojiou176-open/notebooklab (1 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
chamber
Checks that the numbers, capitalised names, and file names in a claim occur in the indexed note. Local, no model. It does not judge meaning.
okf
Open Knowledge Format for Claude: the OKF skill, /okf:gem setup and doctor, and a post-edit hook that runs the okf CLI's validate and lint checks on the bundle you touched.
memex
Zettelkasten-based agent memory system with bidirectional links.
legwork
Decision research for Claude Code and Codex - cited findings where every claim states how well it is supported. Judges a source by whether it suits the claim it backs rather than by its domain, counts corroboration only across genuinely independent sources reached from different search angles, and says so plainly when.
hipocampus
Persistent agent memory that survives across sessions — auto-compacting 3-tier memory with hybrid search. Your agent remembers what it learned, decided, and built.
youtube-knowledge
Search YouTube, read timestamped transcripts, comments and metadata, cut clips, and keep a searchable local library and per channel brains. Runs locally; needs yt-dlp.