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 agentmods add skills/moses607/socialforge/breakout-detectornpx skills add moses607/socialforge --skill breakout-detectorgit clone --depth 1 https://github.com/moses607/socialforgeWhat 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 | $0.00102 | $0.01170 |
| Opus 5 | $0.00051 | $0.00585 |
| Sonnet 5 | $0.00020 | $0.00234 |
| Haiku 4.5 | $0.00010 | $0.00117 |
Grade A, and why
breakout-detector 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 2d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Breakout Detector
Big accounts get big numbers on everything — that is baseline, not signal. A true breakout is a post that beats its own account's normal performance by a wide margin, because that gap is the market voting for a specific idea before the algorithm saturates it. This skill has no live data of its own: the user (or a paired search/scraper tool) supplies recent posts with per-account stats, and you turn that raw list into ranked, normalized breakout patterns plus a brief to make your own version fast. Speed of detection beats precision — a 70%-confidence pattern acted on this week beats a perfect one found after saturation.
1. Gather and normalize
- Collect 30-100 recent posts (last 7-30 days) across 10+ accounts in the niche. For each, require: account follower count, that account's typical/median views, this post's views, and likes+comments+shares+saves.
- Compute the Outlier Score two ways and keep the higher:
View Multiple = post views ÷ that account's median views(best signal; needs per-account baseline).Reach Ratio = post views ÷ follower count(fallback when you lack an account baseline).
- Flag as breakout candidate if View Multiple ≥ 3x OR Reach Ratio ≥ 5x. Discard anything under 2x — it's baseline.
- Kill false positives: drop posts inflated by paid ads, a collab with a far-bigger account, or a one-off news spike unrelated to the niche.
2. Isolate the driver
For each candidate, name the ONE variable most responsible. Score every candidate across:
- Format — carousel, talking-head, green-screen, listicle, B-roll voiceover, text-on-screen.
- Angle/hook — contrarian take, "I was wrong about X", before/after, mistake-confession, us-vs-them.
- Sound/audio — trending sound ID, original VO, specific song. Note if the same sound repeats across candidates.
- Structure — hook <2s, payoff timing, loop, open-loop CTA. Cluster candidates that share a driver. A pattern only counts when 3+ different accounts hit outlier scores using the same driver — one viral post is luck, three is a pattern.
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.
- 2d ago First seen · 64 lines · 102 tokens per session scan A c6e163ded282
breakout-detector is a skill published in the GitHub repository moses607/socialforge (2 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 1,170 once invoked, about $0.0005 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
blog
Full-lifecycle blog engine with 31 sub-skills, 12 content templates, 5-category 100-point scoring, and 5 specialized agents. Routes user requests to the right sub-skill: writing, rewriting, analysis, outlines, audits, schema, charts, images, repurposing, AI citation SEO, FLOW framework prompts, topic-cluster…
blog-notebooklm
Query Google NotebookLM notebooks for source-grounded, citation-backed answers from user-uploaded documents. Manages notebook library, handles Google authentication, and supports smart discovery. Works standalone via /blog notebooklm or internally from blog-write and blog-researcher for source-grounded research…
claude-blog-brain
Scaffold and operate Claude Blog Brain, a source-cited Obsidian brain for blog content creation, optimization, and management dual-optimized for Google rankings (E-E-A-T, the 2026 core updates) and AI citations (GEO/AEO), spanning writing, rewriting and freshness, SERP-informed briefs and outlines, editorial calendars…
blog-google
Google API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature…
banana
Direct, generate, edit, compare, and review visual assets with current Google Gemini image models. Use for image creation, image editing, reference-based consistency, product and character visuals, text-bearing graphics, grounded diagrams, video-derived images, and multi-model image portfolios.
narrator-ai-cli
AI 电影/短剧解说视频自动生成（AI 解说大师 CLI Skill）。当用户需要创建电影解说视频、短剧解说、影视二创、AI 配音旁白视频、film commentary、video narration、drama dubbing、movie narration 时触发。内置电影素材库、BGM、多语种配音、解说模板。通过 narrator-ai-cli 命令行实现：搜片→选模板→选 BGM→选配音→生成文案→合成视频的全流程自动化。CLI client for Narrator AI video narration API.