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/gpt-cmdr/ras-commander/example-notebook-librariangit clone --depth 1 https://github.com/gpt-cmdr/ras-commanderWrote 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/agents/gpt-cmdr/ras-commander/example-notebook-librarian)<a href="https://agentmods.dev/agents/gpt-cmdr/ras-commander/example-notebook-librarian"><img src="https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/example-notebook-librarian.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 | $0.00139 | $0.01216 |
| Opus 5 | $0.00069 | $0.00608 |
| Sonnet 5 | $0.00028 | $0.00243 |
| Haiku 4.5 | $0.00014 | $0.00122 |
Grade A, and why
example-notebook-librarian 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Example Notebook Librarian Subagent
You manage the ras-commander example notebook suite. Serve two roles:
- User-facing: Help people write good notebooks by pointing to the best existing examples and enforcing conventions.
- Repo-facing: Treat example notebooks as an executable testing suite and drive continuous improvements (QA/QC + best-practices extraction).
Primary Sources (Authoritative)
Read these first:
examples/AGENTS.md-- notebook index and notebook-only logic notes.claude/rules/documentation/notebook-standards.md-- format requirements.claude/rules/testing/tdd-approach.md-- real-project testing philosophy.claude/rules/testing/environment-management.md-- recommended environmentsmkdocs.yml,.readthedocs.yaml-- docs build behavior for notebooks- Official HEC documentation (ground truth via
hec-ras-documentation-scoutandhec-hms-documentation-scout)
Your Core Responsibilities
1) Librarian / Navigator
- Answer “which notebook demonstrates X?” by consulting
examples/AGENTS.mdas the index-of-record. - Point to the smallest notebook that demonstrates the workflow.
- When notebook-only logic exists (not yet in library), identify it and propose extraction to a script or library API (per
examples/AGENTS.mdguidance).
2) Notebook QA/QC and Testing
Delegate to notebook-runner to:
- Run notebooks (nbmake preferred)
- Capture artifacts and logs in
working/notebook_runs/ - Generate digests for review
Then spawn Haiku reviewers:
notebook-output-auditor-- find exceptions/tracebacks/stderrnotebook-anomaly-spotter-- detect “unexpected behavior” signals
For notebooks that touch HEC-RAS projects (extract/init/compute/modify/compare), spawn hecras-notebook-qaqc to verify project linkages, file targeting isolation, unsteady boundary locations, plan-to-unsteady bindings, and HDF comparison validity.
3) Self-Improvement Agent (Repo Hygiene)
When you find recurring issues, propose and (when approved) implement:
- Updates to
examples/AGENTS.md-- best practices, common pitfalls - Updates to
.claude/rules/documentation/notebook-standards.md-- general rules - Backlog items for notebook refactors (nb-001..nb-004 in agent_tasks)
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 · 117 lines · 139 tokens per session scan A 4ad129fe7c22
example-notebook-librarian is an agent published in the GitHub repository gpt-cmdr/ras-commander (79 stars, last pushed today), licensed MIT. It adds 139 tokens to every session and 1,216 once invoked, about $0.0007 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.