deltasci

deltasci is a skill for Claude Code, Codex from boheling/deltasci. It costs 117 tokens per session (1,759 once invoked), scanned A, original, MIT.

A research method in which a science specialist and a machine-learning engineer take turns examining an idea. It labels evidence, unknowns, and new proposed connections, then produces a testable hypothesis.

In plain words
What is it for?
Generating and checking research hypotheses across scientific fields, with evidence notes and a measurable condition that could prove each hypothesis wrong.
Why use it?
It helps separate supported facts from gaps in knowledge and creative suggestions, reducing the risk of presenting guesses as established science.

Skill for Claude CodeCodex

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/boheling/deltasci/skill
Any agent
npx skills add boheling/deltasci --skill skill
Clone the repo
git clone --depth 1 https://github.com/boheling/deltasci

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 deltasci

README.md
[![agentmods](https://agentmods.dev/badge/skills/boheling/deltasci/skill.svg)](https://agentmods.dev/skills/boheling/deltasci/skill)
Your own site
<a href="https://agentmods.dev/skills/boheling/deltasci/skill"><img src="https://agentmods.dev/badge/skills/boheling/deltasci/skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,759 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 $0.00117 $0.01759
Opus 5 $0.00059 $0.00879
Sonnet 5 $0.00023 $0.00352
Haiku 4.5 $0.00012 $0.00176

Measured 5d ago against content hash 4fd1daa11f25, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

deltasci 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (install.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skill/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DeltaScience: Two-Perspective Co-Reasoning

Purpose

Generate AI4Science research hypotheses that are:

  1. Grounded — every factual claim is tagged with its evidence type, source, and the AI's self-assessed training coverage.
  2. Honest about AI's epistemic edges — claims outside the AI's training distribution are emitted as KNOWLEDGE_GAP for the researcher, not fabricated.
  3. Explicit about creative leaps — connections the AI is proposing (not citing) are emitted as NOVEL_SYNTHESIS.
  4. Falsifiable — every hypothesis ships with a measurable threshold for being wrong.
  5. Domain-aware — uses a pluggable lens specific to the scientific field.
  6. Two-perspective — alternates between domain expert and ML engineer.

This is the Claude Code skill version of the deltasci Python package. They share the same domain packs and grounding rules.

The three first-class tags

[CLAIM type=<TYPE> coverage=<COVERAGE> source="<CITATION>"]<text>[/CLAIM]
[KNOWLEDGE_GAP category=<CATEGORY>]<question for the researcher>[/KNOWLEDGE_GAP]
[NOVEL_SYNTHESIS rationale="<one-line>"]<the proposed connection>[/NOVEL_SYNTHESIS]

coverage{well-covered, sparse}. uncovered is not allowed on a CLAIM — for that, emit a KNOWLEDGE_GAP instead.

A round with zero KNOWLEDGE_GAPs and zero NOVEL_SYNTHESES is suspect — it suggests the AI is claiming complete certainty across the entire research idea, which is itself a hallucination signal. Synthesis refuses by default.

Inputs

Parameter Required Description
idea Yes The raw research idea.
pack Yes Domain pack name (biomed, materials, climate) or path to a custom pack.
context_dir No Directory of background papers/notes.
out_dir No Where to write outputs. Default: ./deltasci-output/.

Outputs

File Description
transcript.md Full 4-round dialogue with all three tag types.
hypothesis.md Three-section evidence trail (well-covered / sparse / researcher-required) + falsifiability + scorecard.
summary.json Machine-readable hypothesis schema + epistemic summary.

Read the full file on GitHub · 142 lines

Files

What ships with it

7 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.

  1. 5d ago First seen · 142 lines · 117 tokens per session scan A 4fd1daa11f25

Subscribe to this mod's changes

deltasci is a skill published in the GitHub repository boheling/deltasci (143 stars, last pushed 3mo ago), licensed MIT. It adds 117 tokens to every session and 1,759 once invoked, about $0.0006 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 skills, from other repositories

calculator

Evaluate mathematical expressions and unit conversions. Handles arithmetic, percentages, exponents, and common unit conversions (temperature, distance, weight). No external dependencies.

NVIDIA/SkillEvaluator · 32 tokens

paper-graph

Use this skill to map the genealogical lineage and historical progression of a research field. It is designed to visualize the evolutionary path of ideas, showing how technical challenges in earlier works were addressed by subsequent research improvements. The final deliverable is a Markdown file with embedded Mermaid…

EvoScientist/EvoSkills · 197 tokens

paper-navigator

Find and read academic papers (S2 + arXiv). Disambiguate ambiguous queries, search by keyword + citation graph + recommendations + snippets, judge relevance against an authored rubric, and read with L1/L2/L3 strategy. Trigger phrases: find papers, search papers, related work, citation analysis, recent advances, read…

EvoScientist/EvoSkills · 105 tokens

paper-figures

Use this skill to produce standalone, publication-ready PNG graphics and reproducible matplotlib scripts from tabular data (CSVs or DataFrames). This tool is built specifically for rendering numerical data into formal scientific visualizations—including scatter, line, bar, pie, ring, bubble, tornado, KDE, violin, box…

EvoScientist/EvoSkills · 208 tokens

evomath-tao

Use this skill whenever the user submits a non-trivial mathematical claim that needs a rigorous proof or audit. Trigger on IMO/Putnam/USAMO/Olympiad-style problems, ML/AI theoretical statements, research conjectures, suspected-false claims, multi-step proofs the user already failed on, proof drafts with possible…

EvoScientist/EvoSkills · 203 tokens

paper-planning

Guides pre-writing planning for academic papers with 4 structured steps: story design (task-challenge-insight-contribution-advantage), experiment planning (comparisons + ablations), figure design (pipeline + teaser), and 4-week timeline management. Includes counterintuitive planning tactics (write a mock rejection…

EvoScientist/EvoSkills · 166 tokens