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 TheMattBerman/creator-breakout-kit --skill breakout-pattern-researchgit clone --depth 1 https://github.com/TheMattBerman/creator-breakout-kitWrote 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/themattberman/creator-breakout-kit/breakout-pattern-research)<a href="https://agentmods.dev/skills/themattberman/creator-breakout-kit/breakout-pattern-research"><img src="https://agentmods.dev/badge/skills/themattberman/creator-breakout-kit/breakout-pattern-research/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/themattberman/creator-breakout-kit/breakout-pattern-research"><img src="https://agentmods.dev/badge/skills/themattberman/creator-breakout-kit/breakout-pattern-research.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 | $0.00078 | $0.01098 |
| Opus 5.5 | $0.00031 | $0.00439 |
| Sonnet 5.5 | $0.00016 | $0.00220 |
| Haiku 4.5 | $0.00008 | $0.00110 |
Grade A, and why
breakout-pattern-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Breakout Pattern Research
Purpose
Find repeatable breakout content patterns using outlier behavior, not creator popularity.
Package contract
Use from the creator-breakout-kit repo root. Paths are relative to that root.
Primary data source
- Preferred: Virlo or equivalent post-level performance dataset with creator baselines.
- Fallback: manual social review, but label output as constrained and lower confidence.
Evidence limitation
Treat Virlo as metadata-only unless the adapter output explicitly includes transcripts, OCR, frame-level analysis, human-reviewed video notes, or video-intelligence.json. Captions, descriptions, hashtags, topics, thumbnails, and outlier ratios can support pattern hypotheses, but they do not prove what visually happens in a video.
When SCRAPECREATORS_API_KEY and OPENROUTER_API_KEY are configured, run python3 skills/breakout-pattern-research/scripts/video_intelligence.py --run-dir "$RUN_DIR" --limit 3 --max-video-mb 20 after enrichment and before full-kit synthesis. This uses ScrapeCreators plus Gemini to add content DNA for promoted TikTok/Reels posts. It sends video assets inline when they fit under the size cap, otherwise it falls back to metadata/transcript/cover-image inputs.
When audience language would materially improve the brief and VIRLO_API_KEY is configured, optionally run python3 skills/breakout-pattern-research/scripts/virlo_tracking_intelligence.py --research-dir "$RESEARCH_DIR" --limit 3 --track videos --scrape-cadence weekly. Treat virlo-audience-signals.json as comment-derived directional signal, not statistically representative market research. The first run may queue tracking only; rerun the adapter later when Virlo reports are ready.
Inputs
- Category / niche
- Platform focus
- Optional data source notes (Virlo/ScrapeCreators/manual)
- Optional Virlo Tracking audience signals
- Optional brand snapshot for tighter scoring
Outputs
breakout_patterns(3-5)hook_styles(3-5)outlier_evidence_notespattern_confidence_scoressource_postsresearch_mode_used- optional
audience_signals
What ships with it
4 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.
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.
- 1mo ago First seen · 84 lines · 78 tokens per session scan A c76292c2a0a7
breakout-pattern-research is a skill published in the GitHub repository TheMattBerman/creator-breakout-kit (10 stars, last pushed 6mo ago), licensed MIT. It adds 78 tokens to every session and 1,098 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
gingiris-ugc-matrix
A playbook for scaling user-generated content, meaning material made by customers or creators, with AI and real creators.
ai-visibility-audit
When the user wants to know whether their brand or domain is cited in AI answers — AI Overviews, ChatGPT, or AI search — for the queries that matter, and how they stack up against competitors. Also use on "AI visibility audit," "am I cited in AI answers," "do I show up in ChatGPT," "AI Overviews audit," "GEO audit,"…
seo-audit
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking,"…
ai-answer-gap
When the user wants to find the prompts where their brand should be cited in AI answers but isn't — and who owns the answer instead — prioritized by AI search volume so content can attack the biggest gaps first. Also use on "AI answer gap," "AI content gap," "where am I missing from AI answers," "what prompts am I…
llm-mention-tracking
When the user wants to track how often their brand or domain gets mentioned across ChatGPT and AI search engines over a set of prompts, and how that share of voice compares to named competitors over time. Also use on "LLM mention tracking," "track AI mentions," "share of voice in AI," "AI share of voice," "brand…
competitor-profiling
When the user wants to research, profile, or analyze a competitor from its public footprint — site, search/SEO, backlinks, social, and positioning. Also use on "competitor profile," "competitor research," "competitor analysis," "profile this competitor," "analyze competitor," "competitive intelligence," "competitor…