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/offer-cta-architectnpx skills add moses607/socialforge --skill offer-cta-architectgit clone --depth 1 https://github.com/moses607/socialforgeWrote 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/moses607/socialforge/offer-cta-architect)<a href="https://agentmods.dev/skills/moses607/socialforge/offer-cta-architect"><img src="https://agentmods.dev/badge/skills/moses607/socialforge/offer-cta-architect.svg" alt="Measured on agentmods" 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 | $0.00110 | $0.00977 |
| Opus 5 | $0.00055 | $0.00489 |
| Sonnet 5 | $0.00022 | $0.00195 |
| Haiku 4.5 | $0.00011 | $0.00098 |
Grade A, and why
offer-cta-architect 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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Offer & CTA Architect
Selling feels salesy only when the ask arrives before the trust. The fix isn't a better closing line — it's a ladder where each rung is a small, logical next step the audience actually wants to take. Cold viewers don't buy; they engage. Engaged followers don't buy; they join your list. List members buy. First principle: never skip a rung. Ask for the sale from a stranger and you get resistance; ask for a comment and you get momentum you can compound. Money is a lagging indicator of trust you built earlier and elsewhere.
1. Build the CTA ladder
- Attention — the content itself. The CTA is implicit: "keep watching / read to the end." Job: earn reach.
- Micro-commitment — a near-zero-cost action: comment a keyword, save, share, follow. Job: signal interest + feed the algorithm.
- Owned audience — move them off rented land: email list, DM keyword, lead magnet. Job: get permission to contact directly.
- Offer — the paid product/service. Job: convert trust into revenue. Map every post to exactly one rung. A post trying to do all four does none.
2. Match CTA aggression to context
- Reach posts (top of funnel, cold): soft engagement CTA only — "save this", "which one are you?". Selling here suppresses reach and burns trust.
- Nurture posts (warm): give value, then a medium CTA — "full breakdown on my email list, link in bio". You've earned the ask.
- Conversion posts (hot, launch/promo): direct offer, clear price, real urgency, explicit "here's how to buy". No hedging — hot audiences want the door opened. Ratio: roughly give 8-10 times before a hard ask. Track it; if every post sells, you have no audience left to sell to.
3. Engineer lead magnets and the one-CTA rule
- A lead magnet solves ONE narrow, urgent problem in one sitting: checklist, template, swipe file, mini-guide, calculator. Broad = ignored.
- Deliver via keyword-in-comments (DM automation) or link-in-bio; the comment method doubles as an engagement CTA — one action, two wins.
- One CTA per post. Two asks split attention and both lose. If you have two things to say, that's two posts.
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.
- 4d ago First seen · 59 lines · 110 tokens per session scan A 4df525a77df0
offer-cta-architect is a skill published in the GitHub repository moses607/socialforge (2 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 977 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
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…
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"…
self-media-content-delivery
将自媒体创作里程碑保存成文件，管理版本、核验路径、生成完整发布包并更新内容索引。用于保存平台第一版完整成稿、多平台合集、短视频脚本、分镜、定稿、发布包和复盘报告，或用户说“保存一下、整理交付、归档、生成发布清单”时。标题微调、删一句和临时候选不单独保存新版本。.
self-media-trend-radar
安全追踪热点、研究关键词和拆解竞品内容，并将结果转成原创选题和证据包。用于用户要求找热点、看趋势、分析爆款、研究竞品账号、拆标题或开头、比较内容结构、发现评论需求和判断时效窗口。只做公开信息研究和只读采集，不自动互动、发布或使用主账号登录态抓取竞品。.
short-drama
制作多集 AI 微短剧：建立剧集圣经和角色参考，完成分集剧本、逐镜 I2V、对白审计、配音字幕 BGM 与成片，保持跨镜跨集一致性。 当用户说“AI/横屏/竖屏/微短剧、拍短剧、分集剧本、连续剧情视频、做几集短剧”时使用。 单条非剧情视频用 auto-short-video；只写单条脚本用 video-script；只生成一个视频片段用 ai-video-gen。.
multi-voice-dubbing
多角色对话配音：按 cast 和逐行对白为不同角色分配音色与情绪，合成多声线音轨和带角色名字幕。 当用户说“多角色/双人/剧本/对话配音、多人对白、不同角色不同声音、有声剧配音”时使用。 单一公共音色用 tts-voiceover；克隆本人音色用 voice-clone；整部短剧制作由 short-drama 编排。.