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/engagement-boosternpx skills add moses607/socialforge --skill engagement-boostergit 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/engagement-booster)<a href="https://agentmods.dev/skills/moses607/socialforge/engagement-booster"><img src="https://agentmods.dev/badge/skills/moses607/socialforge/engagement-booster.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 | $0.00118 | $0.01263 |
| Opus 5 | $0.00059 | $0.00632 |
| Sonnet 5 | $0.00024 | $0.00253 |
| Haiku 4.5 | $0.00012 | $0.00126 |
Grade A, and why
engagement-booster 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engagement Booster
Algorithms rank content by the engagement it provokes in the first minutes, and every reply, save, and DM is a vote that widens distribution — so treat each post as the opening move of a conversation, not a broadcast. The highest-leverage work happens AFTER you hit publish: the first hour of replies, the discussion you deliberately seed, and the follow-up in DMs. Optimize for comments and saves (the strongest signals) over likes, engineer low-friction ways for people to participate, and turn one-time engagers into a community through repeatable rituals.
1. First-hour tactics (the golden window)
- Be present at publish. Post when your audience is active, then stay for 60 minutes. Early velocity of comments is what triggers the algorithm to expand reach.
- Reply to every comment within minutes, and make replies substantive — a question back, not just "thanks." Each reply is a fresh comment that boosts the count and pulls the commenter back for a second interaction.
- Seed a discussion-starter comment yourself in the first minute: pin a spicy question, a "hot take: ___, agree?", or the #1 objection people will have. This gives lurkers a low-stakes entry point.
- Bake comment-bait into the post. End with a specific, easy question ("A or B?", "what's your #1 ___?") or a fill-in-the-blank. Vague "thoughts?" underperforms concrete binary/list prompts.
2. Reply strategies that grow reach
- Add value, don't just acknowledge. Answer with a bonus tip or resource so the reply is worth reading — screenshotting-worthy replies get shared.
- Always end with a follow-up question to keep the thread alive; longer threads = more signal.
- Pin your best comment (a great question or your seeded starter) to steer the conversation and lift its visibility.
- Reward good comments publicly — heart them, reply with genuine praise, or feature them. This trains your audience that commenting gets noticed, so they do it more.
- Turn objections into content. A recurring question in replies is your next post; tell them so ("great Q — full post coming").
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 · 63 lines · 118 tokens per session scan A b1c36a02913f
engagement-booster is a skill published in the GitHub repository moses607/socialforge (2 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 1,263 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"…
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。.
paper-explainer
科研论文解读：解析 arXiv/PDF 的公式与图表，提炼问题、贡献、方法、关键图和结论，再产出 B站/视频号解读视频或知乎/公众号图文。 当用户说“论文解读、讲论文、论文转视频/图文、科研科普、arXiv、学术视频”时使用。 本 SKILL 从论文做内容；video-to-article 从视频做图文，doc-convert 只转换文档格式。.
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。.
skill-competitor-analysis
分析竞品账号的内容策略，拆解选题、格式、爆款规律和互动模式，输出差异化机会与行动建议。 当用户说"分析竞品""竞品账号""对标账号""拆解爆款""竞品在做什么""对手内容策略""竞争分析"时使用。 和 skill-content-gap-analysis 的区别：本 SKILL 拆解具体竞品账号的内容策略与爆款规律； content-gap-analysis 从赛道整体供需找"没人做好"的蓝海选题空白。.