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/cross-platform-adapternpx skills add moses607/socialforge --skill cross-platform-adaptergit 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 | $0.00096 | $0.01187 |
| Opus 5 | $0.00048 | $0.00593 |
| Sonnet 5 | $0.00019 | $0.00237 |
| Haiku 4.5 | $0.00010 | $0.00119 |
Grade A, and why
cross-platform-adapter 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Platform Adapter
Identical cross-posting loses on every platform because each ranks and rewards different behavior. The winning move is "same idea, native execution": lock ONE core insight (the thing worth saying) and re-package everything around it — length, framing, tone, hook, and caption — to the norms of each surface. Keep the insight and the proof; change the container. A repurpose is a translation, not a copy-paste.
1. Extract the transferable core
- State the ONE insight in a single sentence a stranger could repeat.
- Identify the proof (demo, number, before/after, story beat) — this travels unchanged.
- Write 3 hook angles: contrarian, result-first, and question. You will assign different angles to different platforms.
2. Adapt by platform norms
- YouTube long: 6-12 min, teach-then-payoff, 16:9. Hook in first 15s naming the payoff; retention lives on chapters and open loops. Convert via watch-time + a clear CTA card.
- YouTube Shorts / TikTok: 15-45s, 9:16, fast verbal hook (0-2s), on-screen captions always. TikTok rewards native/lo-fi + trending audio; add a loop or "wait for it." Convert via completion + shares.
- Instagram Reels: 7-30s, 9:16, high-polish, strong first frame + cover text. Carousels (1080x1350) win for how-to; slide 1 is the hook, last slide is the CTA. Convert via saves + shares.
- X: text-first, 1-3 sentences, punchy claim; thread only if the proof needs steps. Native video 1:1 or 9:16, no external links in the main post. Convert via replies + reposts.
- LinkedIn: 150-300 word text post, line breaks every 1-2 sentences, professional but personal; lead with a result or lesson. Convert via comments; ask one question at the end.
- Threads: conversational, lowercase-casual, 1-2 sentences, reply-bait. Convert via replies; no hashtag stuffing.
3. Tune hashtags, captions, and CTA
- Hashtags: TikTok 3-5 niche, IG 3-8 mixed reach, LinkedIn 3 topical, X 0-2, YouTube in description not title, Threads 1.
- Caption first line is a second hook — never waste it on "check out my new video."
- One CTA per post, matched to the platform's convert metric (save/share/comment/watch).
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 · 54 lines · 96 tokens per session scan A 44b896313b7f
cross-platform-adapter is a skill published in the GitHub repository moses607/socialforge (2 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 1,187 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.