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/trend-jackernpx skills add moses607/socialforge --skill trend-jackergit 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 | $0.00101 | $0.01208 |
| Opus 5 | $0.00051 | $0.00604 |
| Sonnet 5 | $0.00020 | $0.00242 |
| Haiku 4.5 | $0.00010 | $0.00121 |
Grade A, and why
trend-jacker 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trend Jacker
Trends are a demand spike the algorithm is already pushing — riding one lets a small account borrow reach it hasn't earned yet, but only if the bridge to your value feels effortless and you arrive before the wave crests. Most trend-jacking fails two ways: forcing an irrelevant trend (cringe, no bridge) or shipping too late (decayed to zero). This skill has no live feed — the user or a paired search tool supplies the current trend and its context; you judge fit, generate on-brand angles, and push to shipped fast. The core discipline: kill bad fits ruthlessly, and when the fit is real, measure time-to-post in minutes, not days.
1. Relevance filter (kill fast)
Score the trend before writing a word. Rate 0-3 each:
- Audience overlap — do the trend's viewers overlap your target audience?
- Bridge strength — is there a natural one-sentence link to your niche/value, no stretch?
- Brand safety — does riding it risk your credibility, or clash with your values/voice? (Score 0 = veto, stop here.)
- Life left — is it still rising, or already peaked and everywhere? Sum /12. 8+ = go. 5-7 = only if you have a genuinely fresh angle. <5 = skip. A forced bridge is worse than silence — it costs trust you can't rebuild.
2. Angle match
Bridge the trend to your value, don't just react to it. Generate 3 angles using these bridges:
- Translate — apply the trend's structure/joke to a problem your audience has ("everyone's doing X; here's X but for ").
- Contrarian — the trend says A; your expertise says "actually, here's why B."
- Insider — what does this trend look like from inside your world? Show the angle only you can. Pick the angle with the strongest bridge + your unique credibility. Draft the hook in the first 2 seconds — the trend reference must land immediately so scrollers recognize it.
3. Speed + cringe-check
- Fast lane (trend → posted in <60 min): 5 min score → 5 min pick angle → 10 min write hook+script → 20 min shoot/assemble on existing assets → 10 min caption+sound+hashtags → 10 min cringe-check + post. Do NOT chase production polish; native/rough beats late-and-slick.
- Cringe-check (60-second gut test): Would you send this to a peer without wincing? Does the bridge feel earned or desperate? Are you late enough that it's already a meme about the trend being dead? Is the audio/reference used correctly? Any "no" → fix or kill.
- Ship same-day. Sounds and memes decay in hours-to-days; news-jacks decay in hours.
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 · 62 lines · 101 tokens per session scan A cc13321b196f
trend-jacker is a skill published in the GitHub repository moses607/socialforge (2 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 1,208 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-write
Write new blog articles from scratch optimized for Google rankings and AI citations. Generates full articles with template selection, answer-first formatting, Key Takeaways summary box, information gain markers, citation capsules, sourced statistics, Pixabay/Unsplash images, built-in SVG chart generation, optional FAQ…
blog-brief
Generate detailed content briefs for blog posts with target keywords, content outlines, competitive analysis, recommended statistics, image and chart suggestions, word count targets, internal linking architecture, template recommendations (12 types), TL;DR drafts, citation capsule planning, information gain prompts…
blog-geo
AI citation readiness audit as part of SEO, covering classic Google search and AI search surfaces together. Use whenever the user wants their content to rank or be cited in ChatGPT, Perplexity, Claude, Gemini, Copilot, You.com, Google AI Overviews, or Google AI Mode. AI citation optimization audit scoring blog posts…
blog-cannibalization
Detect keyword cannibalization across blog posts by extracting primary keywords from titles and headings, clustering semantically similar targets, and flagging posts competing for the same search intent. Supports local-only mode (grep-based) and DataForSEO API mode (Page Intersection endpoint at $0.01/call). Outputs…
blog-schema
Generate complete JSON-LD schema markup for blog posts with Article/BlogPosting, Person, Organization, BreadcrumbList, ImageObject, and optional FAQPage. Validates against Google requirements and warns about deprecated types. Use when user says "schema", "blog schema", "json-ld", "structured data", "schema markup"…
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…