notebook-regression-monitor

notebook-regression-monitor is an agent for Claude Code from equinor/neqsim. It costs 30 tokens per session (337 once invoked), scanned A, original, Apache-2.0.

A monitoring tool for computational notebooks and their saved results. It compares new runs with stored baselines so numerical examples, tables, and figures can be checked over time.

In plain words
What is it for?
Use it to inventory notebooks, compare outputs within tolerances, check generated figures, and report which examples need attention.
Why use it?
It helps detect silent changes, stale figures, broken notebooks, and claims that no longer match computed results.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to inventory notebooks, compare outputs within tolerances, check generated figures, and report which examples need attention.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/equinor/neqsim/notebook_regression_monitor.paperlab
Install

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.

Clone the repo
git clone --depth 1 https://github.com/equinor/neqsim

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-regression-monitor

README.md
[![agentmods](https://agentmods.dev/badge/agents/equinor/neqsim/notebook_regression_monitor.paperlab.svg)](https://agentmods.dev/agents/equinor/neqsim/notebook_regression_monitor.paperlab)
Your own site
<a href="https://agentmods.dev/agents/equinor/neqsim/notebook_regression_monitor.paperlab"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/notebook_regression_monitor.paperlab.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 337 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 $0.00030 $0.00337
Opus 5 $0.00015 $0.00169
Sonnet 5 $0.00006 $0.00067
Haiku 4.5 $0.00003 $0.00034

Measured 3d ago against content hash df6699135ece, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

notebook-regression-monitor 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 3d 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.

neqsim-paperlab/agents/notebook_regression_monitor.paperlab.md · 54 lines

What it actually says

Notebook Regression Monitor Agent

You turn one-time notebook checks into reproducibility monitoring.

Loaded Skills

  • paperlab_notebook_regression_baselines
  • neqsim_in_writing
  • neqsim-notebook-patterns

Required Context

Read these files before analysis when they exist:

  • book.yaml
  • chapter notebook references
  • existing baseline files
  • results.json or lightweight result manifests
  • generated figures and figure dossiers

Workflow

  1. Inventory notebooks and generated figures for the selected book or chapters.
  2. Identify baseline candidates: key scalar outputs, tables, figure files, and hashes or timestamps where appropriate.
  3. Run selected notebooks only when needed and feasible; classify expensive notebooks as expensive-skip with a required manual command.
  4. Compare outputs against tolerances and classify notebooks as pass, stale, broken, missing-baseline, or expensive-skip.
  5. Report stale figures and chapter claims that no longer match notebook output.

Output

  • replication_status.json
  • stale_figure_alert.md
  • updated baseline recommendations

Guardrails

  • Do not overwrite baselines without explicit approval.
  • Prefer small scalar baselines over full notebook diffs.
  • Record NeqSim and Python environment details when executing notebooks.
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. 3d ago First seen · 54 lines · 30 tokens per session scan A df6699135ece

Subscribe to this mod's changes

notebook-regression-monitor is an agent published in the GitHub repository equinor/neqsim (150 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 337 once invoked, about $0.0002 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 2026-09-03.

Related

Other agents, from other repositories

ai-hygiene-auditor

Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.

athola/claude-night-market · 48 tokens

tester

A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.

Insajin/autopus-adk · 38 tokens

test-writer

Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…

HirogaKatageri/hirokata · 77 tokens

verify-app

Full verification - unit tests, migration check, lint, types.

pablomarin/claude-codex-forge · 15 tokens

tester

Executes tests based on TESTSTRATEGY.md and feature-level TEST.md. Runs unit/integration tests via test runner, reports results, and updates TEST.md checklists. In TDD mode, generates TEST.md skeletons during /spec. In post-dev mode, generates TEST.md and test code after /dev completion.

ByeongminLee/nextjs-claude-code · 67 tokens

test-engineer

Tessa - The Skeptic 🧪. Test engineer who assumes nothing works until proven otherwise. Invoke proactively when new code is written or modified. Generates comprehensive test coverage for unit, integration, and end-to-end scenarios. Catches bugs before production.

TechNickAI/claude_telemetry · 55 tokens