A routing and evidence workflow for natural-science and engineering work, including simulations, scientific software, dataset analysis, model fitting, and high-performance computing. It records the work and supporting evidence in a science evidence graph.

Use it to organize solver runs, analyze scientific data, check packages and environments, validate units or convergence, work with HPC systems, and support evidence-backed claims.

It helps choose suitable software and reference paths while keeping computational results, checks, and scientific claims traceable.

science — Skill for Claude Code and Codex by ResearAI: A routing and evidence workflow for natural-science and engineering…

About the project

DeepScientist is a local research studio that manages the cycle from baseline experiments through research findings and paper-ready outputs. Researchers use it to organize autonomous scientific investigations, review progress, and take control when needed. The catalogue add-ons provide workflows and agent integrations for running research projects with it.

ResearAI/DeepScientist · 3,315 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/researai/deepscientist/science

Any agent

npx skills add ResearAI/DeepScientist --skill science

Clone the repo

git clone --depth 1 https://github.com/ResearAI/DeepScientist

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/researai/deepscientist/science.svg)](https://agentmods.dev/skills/researai/deepscientist/science)

Your own site

<a href="https://agentmods.dev/skills/researai/deepscientist/science"><img src="https://agentmods.dev/badge/skills/researai/deepscientist/science.svg" alt="Measured on agentmods" height="20"></a>

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,727 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.

Model	Per session	Once invoked
Fable 5.1	$0.00070	$0.01727
Opus 5	$0.00035	$0.00864
Sonnet 5	$0.00014	$0.00345
Haiku 4.5	$0.00007	$0.00173

Measured 6d ago against content hash 4d61b39e63d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

science 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.

src/skills/science/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Science

One-Sentence Summary

Use bash_exec(...) to do the real scientific work, use this skill to choose the right package/reference path, and use artifact.science(...) to record the durable Science Evidence Graph.

Match Signals

Use this skill when the task includes any of these signals:

natural science, engineering, simulation, scientific software, numerical solver, HPC, SLURM, SSH, model fitting, or dataset analysis
package names such as PySCF, LAMMPS, OpenMM, GROMACS, MEEP, Scanpy, Astropy, Geant4, OpenFOAM, CP2K, ABINIT, or similar scientific packages
requests to verify an environment, run a solver, reproduce a computational result, analyze scientific data, validate units/convergence/schema, or make a scientific claim
SetupAgent needs to organize a science task into a Copilot handoff or autonomous startup brief

Control Surface

Real execution: always bash_exec(...).
Evidence records: artifact.science(...) under the existing artifact MCP namespace.
User-visible milestones or blockers: artifact.interact(...).
Package knowledge: this skill's references and package cards.
Do not create a top-level science MCP namespace.
Do not migrate FermiLink runner, HPC profile manager, CLI workflow, FastAPI backend, Chainlit UI, or source implementation into DeepScientist runtime.

Progressive Disclosure

Read only the references needed for the active task:

references/package-index.min.json: compact index of the 169 package cards; search this first when a package/domain is unclear.
references/domain-index.md: human-readable grouping by inferred scientific domain.
references/packages/<package_id>.md: package-specific routing card with knowledge URL, source URL, package-check pattern, expected science nodes, evidence paths, and pitfalls.
references/package-check-playbook.md: package availability checks before treating a solver as usable.
references/artifact-science-tool.md: exact artifact.science(...) contract and examples.
references/hpc-via-bash-exec.md: SSH, scheduler, queue, and remote-log discipline through bash_exec(...).
references/claim-type-discipline.md: computed / parsed / digitized / hypothesis claim discipline.
references/science-task-brief-template.md: SetupAgent and startup brief shape; use as context, not as a required goal.md file.

Read the full file on GitHub · 138 lines

Files

What ships with it

60 files 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.

6d ago First seen · 138 lines · 70 tokens per session scan A 4d61b39e63d9

Subscribe to this mod's changes

science is a skill published in the GitHub repository ResearAI/DeepScientist (3,315 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,727 once invoked, about $0.0003 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.

Scientific

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens