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.
npx skills add Avyayalaya/agent-prime --skill deep-domain-learninggit clone --depth 1 https://github.com/Avyayalaya/agent-primeWrote 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.
[](https://agentmods.dev/skills/avyayalaya/agent-prime/deep-domain-learning)<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.
<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>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 | $0.00071 | $0.06677 |
| Opus 5 | $0.00036 | $0.03338 |
| Sonnet 5 | $0.00014 | $0.01335 |
| Haiku 4.5 | $0.00007 | $0.00668 |
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.
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.
- 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.
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.
- 9d ago First seen · 478 lines · 71 tokens per session scan A b124952c42ef
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.
Other skills, from other repositories
Learn
When the principal is in learning mode (reading a repo, watching a talk, processing a new tool), /learn takes a brief input and produces a structured note in vault/concepts/learning/ with category, modern-stack location, relevance verdict, and reconsideration triggers. Captures the value of every learning sweep…
openspec-onboard
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
gsd-help
Show available GSD commands and usage guide.
oma-explanation
An offline HTML document that teaches a reader what changed in code, using background information, simple examples, a code walkthrough, and a quiz.
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.
project-context
Use PowerContext project memory and handoff tools through MCP when continuing prior work, recalling decisions, maintaining durable memory, or transferring work across tasks, sessions, or agents.