deep-domain-learning

deep-domain-learning is a skill for Claude Code, Codex from Avyayalaya/agent-prime. It costs 71 tokens per session (6,677 once invoked), scanned A, original, MIT.

A method for learning an unfamiliar subject deeply from basic principles. It builds an explanatory model that connects causes, mechanisms, measurements, and likely outcomes.

In plain words
What is it for?
Understanding a new domain, preparing for expert conversations, building research or investment foundations, and giving an AI agent the context needed for better analysis.
Why use it?
It helps when a quick summary is not enough and you need to predict, diagnose, design, or discuss work in a new field with confidence.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; mentions Codex.

Good fit Understanding a new domain, preparing for expert conversations, building research or investment foundations, and giving an AI agent the context needed for better analysis.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/avyayalaya/agent-prime/deep-domain-learning
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.

Any agent
npx skills add Avyayalaya/agent-prime --skill deep-domain-learning
Clone the repo
git clone --depth 1 https://github.com/Avyayalaya/agent-prime

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 deep-domain-learning

README.md
[![agentmods](https://agentmods.dev/badge/skills/avyayalaya/agent-prime/deep-domain-learning/github.svg)](https://agentmods.dev/skills/avyayalaya/agent-prime/deep-domain-learning)
Your own site
<a href="https://agentmods.dev/skills/avyayalaya/agent-prime/deep-domain-learning"><img src="https://agentmods.dev/badge/skills/avyayalaya/agent-prime/deep-domain-learning/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for deep-domain-learning

Your own site · 80×15
<a href="https://agentmods.dev/skills/avyayalaya/agent-prime/deep-domain-learning"><img src="https://agentmods.dev/badge/skills/avyayalaya/agent-prime/deep-domain-learning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,677 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 $0.00071 $0.06677
Opus 5 $0.00036 $0.03338
Sonnet 5 $0.00014 $0.01335
Haiku 4.5 $0.00007 $0.00668

Measured 9d ago against content hash b124952c42ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

deep-domain-learning 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 9d 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.

shared/toolkits/skills/deep-domain-learning/SKILL.md · 478 lines

How it starts

The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Produce a deep, mechanistic World Model of any domain — a structured narrative document that enables the reader to predict, explain, diagnose, design, and feel the inevitability of outcomes in that domain. The output is not a summary or survey; it is a first-principles construction that traces every mechanism to bedrock.

When to Use / When NOT to Use

Use this skill when:

  • Learning a new domain deeply enough to reason from first principles (not just recall facts)
  • Preparing for expert-level conversations, keynotes, or advisory work in an unfamiliar field
  • Building the conceptual foundation for a thesis, investment analysis, or product strategy
  • An agent needs domain context before producing high-quality synthesis or analysis
  • You need to identify where your intuitions about a domain are wrong

Do NOT use this skill when:

  • You need a quick overview or executive summary (ask directly — this produces 10K-30K words)
  • The domain is already well-understood by the reader (use Research Synthesis skill instead)
  • You need tactical how-to instructions, not conceptual understanding (use a tutorial)
  • The topic is narrow enough for a single Q&A exchange
  • You need current news or market data (this produces timeless mechanistic understanding, not current events)

Anti-inputs (what this skill does NOT handle):

  • Competitive analysis or market sizing (→ Competitive & Market Analysis skill)
  • Specification of what to build (→ Specification Writing skill)
  • Synthesis of multiple existing research papers (→ Research Synthesis skill)
  • Opinion formation or thesis construction (→ Synthesizer agent)

Format Rules (Read First)

These rules govern every World Model document. They are not style preferences — they are quality enforcement mechanisms derived from iterative testing of domain learning outputs.

  1. Dense explanatory prose, not bullet lists. Bullet lists are permitted ONLY for enumeration after narrative explanation. The primary content is flowing paragraphs that build understanding incrementally. A World Model that reads like a slide deck has failed.

Read the full file on GitHub · 478 lines

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. 9d ago First seen · 478 lines · 71 tokens per session scan A b124952c42ef

Subscribe to this mod's changes

deep-domain-learning is a skill published in the GitHub repository Avyayalaya/agent-prime (8 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 6,677 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 2026-08-31.