scienceworld-tool-user

scienceworld-tool-user is a skill for Claude Code, Codex from zjunlp/SkillNet. It costs 87 tokens per session (461 once invoked), scanned A, original, MIT.

A tool-use step for ScienceWorld, a simulated environment for science experiments. It applies an instrument from the inventory to a named object or location and reads the result.

In plain words
What is it for?
Use it when an experiment requires a tool to change or inspect something in the environment.
Why use it?
It removes the need to coordinate the tool, target, and environment command manually. This helps perform actions such as digging, cutting, heating, or measuring.

Skill for Claude CodeCodex

About the project

SkillNet is infrastructure for finding, creating, evaluating, combining, and coordinating reusable capabilities for AI agents. Agent developers use it as a searchable and installable library of skills and as a system for selecting skills for particular tasks. The catalogue contains skills that can be discovered, installed, or used with SkillNet.

zjunlp/SkillNet · 1,253 stars · on GitHub

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 skills/zjunlp/skillnet/scienceworld-tool-user
Any agent
npx skills add zjunlp/SkillNet --skill scienceworld-tool-user
Clone the repo
git clone --depth 1 https://github.com/zjunlp/SkillNet

Made for: Claude Code, Codex.

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 scienceworld-tool-user

README.md
[![agentmods](https://agentmods.dev/badge/skills/zjunlp/skillnet/scienceworld-tool-user.svg)](https://agentmods.dev/skills/zjunlp/skillnet/scienceworld-tool-user)
Your own site
<a href="https://agentmods.dev/skills/zjunlp/skillnet/scienceworld-tool-user"><img src="https://agentmods.dev/badge/skills/zjunlp/skillnet/scienceworld-tool-user.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 461 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 $0.00087 $0.00461
Opus 5 $0.00044 $0.00230
Sonnet 5 $0.00017 $0.00092
Haiku 4.5 $0.00009 $0.00046

Measured yesterday against content hash b0402aa357cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scienceworld-tool-user 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 yesterday.

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.

experiments/src/skills/scienceworld/scienceworld-tool-user/SKILL.md · 39 lines

What it actually says

Skill: Tool User

Purpose

Perform a physical action on the environment using a tool from your inventory. The core action is use TOOL on TARGET.

When to Use

  • A task requires modifying the environment (digging, cutting, heating).
  • You need to measure a property of an object (temperature, conductivity).
  • A tool-based interaction is the next step in your experiment workflow.

Core Workflow

  1. Ensure Tool in Inventory: The required tool (e.g., shovel, thermometer, axe) must be in your inventory. Use pick up OBJ if it is not.
  2. Identify Target: Determine the exact target object or location name (e.g., ground, tree, metal fork).
  3. Execute: use TOOL on TARGET.
  4. Interpret Result: Read the observation output to determine the outcome (e.g., temperature reading, state change).

Key Actions

Action Purpose
pick up OBJ Acquire tool if not in inventory
use OBJ on OBJ Perform tool interaction
look around Confirm target identity and location

Example

Task: Measure the temperature of a metal fork using a thermometer.

  1. pick up thermometer — ensure tool is in inventory
  2. use thermometer on metal fork
  3. Observation: "a thermometer, currently reading a temperature of 72 degrees celsius"

Important Notes

  • The tool must be in your inventory before use. The pick up action is a prerequisite.
  • Use exact object names as they appear in the environment description.
  • Some tools produce measurable outputs (thermometer readings); others produce state changes (shovel digs soil). Interpret accordingly.
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 39 lines · 87 tokens per session scan A b0402aa357cc

Subscribe to this mod's changes

scienceworld-tool-user is a skill published in the GitHub repository zjunlp/SkillNet (1,253 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 461 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 2026-09-03.

Related

Other skills, from other repositories

ddr-globem-analysis

Analyze a specific participant's longitudinal passive-sensing and psychological data in the GLOBEM digital depression research dataset. Use this skill whenever the task involves: analyzing a user's mental health or behavioral data from wearables/smartphones, generating QA pairs about behavioral/psychological changes…

zjunlp/DataMind · 98 tokens

mimic-iv-patient-analysis

Comprehensive strategy for analyzing individual patient records in MIMIC-IV EHR database and generating high-quality, diverse QA pairs. Use this skill whenever the task involves analyzing a specific patient's clinical data from MIMIC-IV (or similar EHR databases), querying across hospital and ICU tables, and…

zjunlp/DataMind · 118 tokens

globem-user-analysis

Comprehensive individual-user analysis on the GLOBEM dataset — a longitudinal passive-sensing + mental-health study of college students. Use this skill whenever a task involves analyzing a specific participant (e.g. "Analyze user INS-W002") from the GLOBEM dataset, exploring behavioral patterns from smartphone…

zjunlp/DataMind · 88 tokens

mimic-patient-analysis

Comprehensive patient analysis using the MIMIC-IV clinical database. Use this skill whenever asked to analyze, summarize, or investigate a patient's medical history, hospital admissions, diagnoses, medications, procedures, or clinical course from a MIMIC-IV SQLite database. Triggers on prompts like "Analyze patient…

zjunlp/DataMind · 100 tokens

auto-experiment

Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENTPLAN.md, routes mechanism family inline (Phase 1.5), implements experiment code, deploys to GPU, and collects initial results. Use when user says "implement experiments", "experiment", "deploy the plan", or has an experiment plan ready to…

zjunlp/Mechanist · 75 tokens

hypothesis-batch

Automated pipeline for generating and refining multiple research hypotheses.

zjunlp/Mechanist · 16 tokens