What is rapid-domain-mastery?

A specialized agent for understanding unfamiliar fields from multiple sources. It builds mental models, identifies disagreements and prerequisites, and can tutor through oral-exam-style questions.

Use it for research onboarding, exam preparation, corpus-based learning, misconception diagnosis, and interactive tutoring.

It helps distinguish real understanding from memorization and keeps uncertainty visible when the available sources are incomplete.

rapid-domain-mastery — Agent for Claude Code by Emily2040

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.

Clone the repo

git clone --depth 1 https://github.com/Emily2040/rapid-domain-mastery

Made for: Claude Code.

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/agents/emily2040/rapid-domain-mastery/rapid-domain-mastery/github.svg)](https://agentmods.dev/agents/emily2040/rapid-domain-mastery/rapid-domain-mastery)

Your own site

<a href="https://agentmods.dev/agents/emily2040/rapid-domain-mastery/rapid-domain-mastery"><img src="https://agentmods.dev/badge/agents/emily2040/rapid-domain-mastery/rapid-domain-mastery/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/emily2040/rapid-domain-mastery/rapid-domain-mastery"><img src="https://agentmods.dev/badge/agents/emily2040/rapid-domain-mastery/rapid-domain-mastery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 215 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.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.00215
Opus 5.5	$0.00014	$0.00086
Sonnet 5.5	$0.00007	$0.00043
Haiku 4.5	$0.00003	$0.00021

Measured 2mo ago against content hash bc70bd02b33b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rapid-domain-mastery 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 2mo 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.

.github/agents/rapid-domain-mastery.agent.md · 34 lines

What it actually says

Use this agent when the task is learning and reasoning from a corpus, not just editing code.

Core behavior

Audit the corpus before making broad claims.
Build a field map:
- core mental models
- expert disagreements
- open questions
- prerequisites
Generate diagnostic questions that separate memorization from understanding.
If the user engages interactively, switch into tutor mode.
Keep epistemic status explicit:
- consensus
- debate
- open
- prerequisite
- inference
- gap

Anti-patterns

Do not:

produce a chapter summary and pretend that is expertise
invent disputes not grounded in the corpus
hide uncertainty when the sources are thin

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.

2mo ago First seen · 34 lines · 35 tokens per session scan A bc70bd02b33b

Subscribe to this mod's changes

rapid-domain-mastery is an agent published in the GitHub repository Emily2040/rapid-domain-mastery (17 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 215 once invoked, about $0.0001 per session on Opus 5.5. 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.

Learning and teaching Multi-Agent Research agent-skills ai-agents learning mental-models prompt-engineering

rapid-domain-mastery next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rapid-domain-masteryEmily2040/rapid-domain-mastery	Agent	17	5mo ago	MIT	A	35	Claude Code
VSCode Tour Expertgithub/awesome-copilot	Agent	41k	today	MIT	A	23	Claude Code
Sensei - Junior Mentorgithub/awesome-copilot	Agent	41k	today	MIT	A	43	Claude Code
Microsoft Learn Contributorgithub/awesome-copilot	Agent	41k	today	MIT	A	27	Claude Code
dotnet-fullstack-mentorgithub/awesome-copilot	Agent	41k	today	MIT	A	39	Claude Code
interview-prepgithub/awesome-copilot	Agent	41k	today	MIT	A	32	Claude Code
Microsoft Study and Learngithub/awesome-copilot	Agent	41k	today	MIT	A	22	Claude Code