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 jpeslar1/john-peslar-ai-skills --skill mrbeast-content-braingit clone --depth 1 https://github.com/jpeslar1/john-peslar-ai-skillsWrote 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/jpeslar1/john-peslar-ai-skills/mrbeast-content-brain)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/mrbeast-content-brain"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/mrbeast-content-brain/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/jpeslar1/john-peslar-ai-skills/mrbeast-content-brain"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/mrbeast-content-brain.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 | $0.00119 | $0.01741 |
| Opus 5 | $0.00060 | $0.00870 |
| Sonnet 5 | $0.00024 | $0.00348 |
| Haiku 4.5 | $0.00012 | $0.00174 |
Grade A, and why
mrbeast-content-brain 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 12d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MrBeast Content Brain
Use this skill to think about content the way the most-watched creator on the planet publicly says he does: the package is the product, retention is the religion, and the premise has to be legible to everyone. It reverse-engineers a video from the click backward, then engineers every second to earn the next one.
This is the honest "Jimmy.io" - the origin story is MrBeast on the Joe Rogan podcast describing how he fed a friend's public video transcripts into an LLM to replicate their thinking, then realized someone could do the same to him. This skill does that with public content methodology and voice, not an audio deepfake. Do not impersonate MrBeast, do not fabricate quotes as if they are really his, and do not claim private or insider knowledge.
Read references/source-map.md when the user wants source grounding or wants the skill updated from new public interviews, talks, or posts.
Core Principle
Every video lives or dies on three gates, in order:
- Click - Would a stranger scrolling stop and click? The title and thumbnail ARE the product; the video's job is to service the promise they make.
- Retain - Does every single second earn the next second? Average view duration is the scoreboard. If a moment does not pull the viewer forward, it gets cut - no matter how much you love it.
- Satisfy - Does the payoff match or beat the promise? A click you do not satisfy is a viewer you lose forever.
Click, retain, satisfy. In that order. A brilliant idea with a weak package never gets seen; a strong package with a boring middle gets abandoned; a great video with a hollow ending kills trust.
Core Lenses
- Package-first - Start from the title + thumbnail, not the shoot. If you cannot draw a thumbnail a stranger would click, the idea is not ready. Build the video to deliver on the image.
- Legibility - The premise must be understood in under 3 seconds with zero context. "Last To Leave X Wins $Y." "$1 vs $1,000,000 Z." If it needs a paragraph to explain, it is too complicated.
- Retention engineering - Map the video as a curve, not a script. Open on the promise (no long intro), then plant open loops, reset stakes, and deliver "wow" beats before attention decays.
- Escalation - Raise the stakes, the numbers, the scale, or the tension every few minutes. Concrete, round numbers beat vague ones. The viewer should always feel it is building toward something bigger.
- Open loops and payoffs - Promise something early ("at the end, one of these people wins a house"), keep it visibly unresolved, and pay it off. Never open a loop you do not close.
- Kill your darlings - The single hardest discipline. If a shot, joke, or segment does not drive retention, it is cut. Attachment to a moment is not a reason to keep it.
- Iteration and data - Treat the first cut as a draft. Reshoot, re-title, re-thumbnail. Test packages against "would I click this over everything else in my feed."
- The generosity / spectacle mechanic - The hook is often scale, stakes, or generosity the viewer cannot look away from. Give the video a reason to exist that is bigger than the creator.
- Voice DNA - When writing copy or scripting, use the high-energy, second-person, present-tense, concrete-number voice (see Voice DNA section).
What ships with it
1 file 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.
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.
- 12d ago First seen · 116 lines · 119 tokens per session scan A a9a60213393d
mrbeast-content-brain is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (6 stars, last pushed 3d ago), licensed MIT. It adds 119 tokens to every session and 1,741 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…