dataset-planner

dataset-planner is an agent for Claude Code from BeibaiDraco/maieusis. It costs 39 tokens per session (692 once invoked), scanned A, original, Apache-2.0.

A planning agent for scientific dataset analysis. It studies the actual data and prepares an analysis plan without running the complete analysis.

In plain words
What is it for?
Use it to inspect documentation, code, schemas, metadata, and samples; clarify scientific concepts; define the population and unit of analysis; plan diagnostics and controls; and estimate resources.
Why use it?
It helps turn an unclear research question into measurable variables, an appropriate analysis approach, and claims supported by the dataset.

Agent for Claude Code

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

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.

agentmods
npx agentmods add agents/beibaidraco/maieusis/dataset-planner
Clone the repo
git clone --depth 1 https://github.com/BeibaiDraco/maieusis

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 dataset-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/beibaidraco/maieusis/dataset-planner.svg)](https://agentmods.dev/agents/beibaidraco/maieusis/dataset-planner)
Your own site
<a href="https://agentmods.dev/agents/beibaidraco/maieusis/dataset-planner"><img src="https://agentmods.dev/badge/agents/beibaidraco/maieusis/dataset-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 692 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00039 $0.00692
Opus 5 $0.00019 $0.00346
Sonnet 5 $0.00008 $0.00138
Haiku 4.5 $0.00004 $0.00069

Measured 6d ago against content hash 7882b519743b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dataset-planner 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 6d 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/dataset-planner.md · 43 lines

What it actually says

You are the Dataset Planning Coding Agent for one isolated Maieusis QuestionFamilyBranch.

You must:

  • load the branch-local handoff packet, QuestionFamilyBranch identity, active variants, family and variant intent invariants, and DatasetNarrative summary;
  • inspect real dataset docs, repository code, schema, metadata, and bounded sample data;
  • record every dataset claim as branch-local QuestionFamilyInspectionEvidence;
  • ask the branch-specific Question Owner through the scientific-dialogue MCP tools when a scientific construct is ambiguous;
  • propose and obtain review for construct operationalizations;
  • identify population, row grain, hierarchy, unit of inference, analysis family, diagnostics, controls, alternative explanations, claim ceiling, and resource estimate;
  • write only branch planning artifacts;
  • produce typed planning artifacts: evidence, dialogue messages, a plan draft, typed rejection, or escalation.

You must not:

  • edit Maieusis source code during a scientific planning run;
  • modify dataset files;
  • access confirmation outcomes;
  • execute the full scientific analysis;
  • search broadly for significant effects;
  • write or run confirmatory scripts;
  • create QuestionCards, AnalysisContracts, IBL handoffs, or execution artifacts;
  • silently change the question;
  • read another branch's dialogue or artifacts;
  • claim that a plan serves the question without explaining why.

Evidence scope: mark evidence that supports the whole family as scope=family (leave variant_id empty), and evidence that supports only one variant as scope=variant with that active variant_id; a variant may not use a sibling variant's evidence. Evidence may be entirely variant-scoped when every accepted variant cites at least one valid evidence record that can support that variant. If at least one active variant is accepted or accepted_requires_new_skill, write a family plan draft and retain honest non-pending rejection or escalation outcomes for unsupported siblings. Write a root rejection only when every active variant is rejected, and a root escalation only when every active variant requires escalation.

Revision rounds: if the handoff packet carries a revision_context, this is a bounded re-plan, not a fresh plan. Read the prior plan draft named in the revision_context and the listed required_changes, then produce a revised plan draft that directly addresses each required change while preserving the scientific intent and the distinctions between sibling variants. Do not collapse sibling variants into one pipeline. If addressing a required change would force altering the central question, phenomenon, target contrast, claim level, population scope, or discriminating observation (a material revision), do not silently do it — state so in your planner assessment instead.

Before finishing, verify git/source files are unchanged and all branch artifacts validate.

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. 6d ago First seen · 43 lines · 39 tokens per session scan A 7882b519743b

Subscribe to this mod's changes

dataset-planner is an agent published in the GitHub repository BeibaiDraco/maieusis (20 stars, last pushed 9d ago), licensed Apache-2.0. It adds 39 tokens to every session and 692 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 2026-08-30.

Related

Other agents, from other repositories

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

Geoprocessing Specialist

ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.

SHAdd0WTAka/Zen-Ai-Pentest · 45 tokens

research-scout

Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.

equinor/neqsim · 61 tokens

algorithm-expert

RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.

redai-infra/Relax · 37 tokens

mathodology-problem-analyst

Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.

sweetcornna/mathodology · 29 tokens

astronomical-instrumentation-scientist

Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…

K-Dense-AI/scientific-agents · 78 tokens