ras-commander: Agent for Claude Code

.claude/agents/notebook-anomaly-spotter.md

notebook-anomaly-spotter is an agent for Claude Code from gpt-cmdr/ras-commander. It costs 80 tokens per session (433 once invoked), scanned A, original, MIT.

A reviewer for condensed reports from executed Jupyter notebooks. Jupyter notebooks combine code, explanations, and results in one interactive document.

In plain words
What is it for?
Use it to review notebook audit files, identify the affected cells, explain why results look wrong, and suggest tests or debugging steps.
Why use it?
It finds suspicious results even when the notebook reports no error, such as empty output, missing files, unexpected zeros, NaN values, leaked machine paths, or meaningful warnings.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is gpt-cmdr/ras-commander's own configuration. It tells Claude Code how to work on ras-commander itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ras-commander configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gpt-cmdr/ras-commander. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gpt-cmdr/ras-commander/main/.claude/agents/notebook-anomaly-spotter.md
Clone the repo
git clone --depth 1 https://github.com/gpt-cmdr/ras-commander

Made for: Claude Code.

Wrote 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.

agentmods badge for notebook-anomaly-spotter

README.md
[![agentmods](https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/notebook-anomaly-spotter/github.svg)](https://agentmods.dev/agents/gpt-cmdr/ras-commander/notebook-anomaly-spotter)
Your own site
<a href="https://agentmods.dev/agents/gpt-cmdr/ras-commander/notebook-anomaly-spotter"><img src="https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/notebook-anomaly-spotter/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.

agentmods 80×15 button for notebook-anomaly-spotter

Your own site · 80×15
<a href="https://agentmods.dev/agents/gpt-cmdr/ras-commander/notebook-anomaly-spotter"><img src="https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/notebook-anomaly-spotter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 433 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00080 $0.00433
Opus 5 $0.00040 $0.00217
Sonnet 5 $0.00016 $0.00087
Haiku 4.5 $0.00008 $0.00043

Measured 9d ago against content hash aab6eec69b91, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

notebook-anomaly-spotter 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 9d 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.

.claude/agents/notebook-anomaly-spotter.md · 51 lines

What it actually says

Notebook Anomaly Spotter (Haiku)

Review digests of notebook runs, not full notebooks. Flag “unexpected behavior” signals even when no exception occurs.

Input You Expect

Consume files created by scripts/notebooks/audit_ipynb.py:

  • audit.md
  • audit.json

What You Flag (Even If “Green”)

Prioritize these high-signal anomalies:

  • Outputs implying emptiness: “0 rows”, “empty”, “no data”, “None”, “NaN”
  • Missing artifacts: “HDF not created”, “file not found”, “no maps generated”
  • Suspicious invariants: min==max where variability expected, all zeros
  • Absolute path leakage in outputs (usernames, machine-specific paths)
  • Warnings indicating wrong behavior (projection mismatches, CRS issues, deprecations that change semantics, shapely/geopandas warnings)

Output Format

Report these items for each notebook:

  • List anomalies with cell index and a short quote
  • Explain why each is suspicious (expected behavior vs observed)
  • Recommend remediation:
    • Add/strengthen assertions in notebook
    • Print key intermediate summaries
    • Switch to RasExamples pattern / parameterized paths
    • Delegate to example-notebook-librarian for conventions

Cross-References

Agents (collaborate with):

  • notebook-runner -- Executes notebooks before you spot anomalies
  • notebook-output-auditor -- Complementary: it finds errors, you find anomalies
Changes

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.

  1. 9d ago First seen · 51 lines · 80 tokens per session scan A aab6eec69b91

Subscribe to this mod's changes

notebook-anomaly-spotter is an agent published in the GitHub repository gpt-cmdr/ras-commander (79 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 433 once invoked, about $0.0004 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.