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/profile-optimizernpx skills add moses607/socialforge --skill profile-optimizergit 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 | $0.00962 |
| Opus 5 | $0.00051 | $0.00481 |
| Sonnet 5 | $0.00020 | $0.00192 |
| Haiku 4.5 | $0.00010 | $0.00096 |
Grade A, and why
profile-optimizer 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 yesterday.
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.
Profile Optimizer
A profile is a landing page, not a diary. Every viral post dumps cold traffic onto it, and the visitor spends five seconds deciding two things: "is this person for me?" and "what do I do next?" If the answer isn't obvious, they leave and never come back. Optimize for that stranger, not for your existing fans. First principle: one clear promise beats a clever vibe every time. Ambiguity is the tax you pay on every impression.
1. Audit against the 5-second test
- Screenshot the profile. Show it to someone (or the model) for 5 seconds, then hide it.
- Ask: "Who do I help? What outcome do I deliver? Why follow now?" If they can't answer all three, the profile fails.
- Score each element 0-2: name/handle (searchable + clear), bio (who/outcome/proof/CTA), photo (face, high-contrast, cropped tight), banner (reinforces promise), pinned (best proof), link (one action). Anything under 2 gets rewritten.
2. Rewrite each element to a formula
- Name field (not just handle):
Name | What you do. The name field is searchable — load it with your niche keyword, e.g. "Maya | Duck-Farm Systems". - Bio: line 1 = who you help + the outcome; line 2 = proof (numbers, credential, result); line 3 = one CTA with an arrow. Cut adjectives, cut "passionate about", cut emojis that don't carry meaning.
- Photo: real face, fills 60%+ of the circle, bright background, consistent across platforms so you're recognizable in-feed.
- Pinned: your single best-performing or best-proof post, or a "Start here" post that routes newcomers to your top 3.
3. Build the link-in-bio funnel
- Pick ONE primary action (email list, lead magnet, product). Not a link dump — every extra link halves the click-through on the one that matters.
- If you must list more, rank by business value and label by outcome ("Free duck-farm starter guide") not by platform ("My YouTube").
- Match the bio CTA to the destination exactly. Broken promises between bio and link kill conversion.
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.
- yesterday First seen · 59 lines · 102 tokens per session scan A abb01eaabfe3
profile-optimizer 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 962 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-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"…
blog-audio
Generate audio narration of blog posts using Google Gemini TTS. Supports summary narration, full article read-aloud, and two-speaker podcast/dialogue mode with 30 voice options. Outputs MP3 with HTML5 audio embed code. Works standalone via /blog audio or internally from blog-write. Falls back gracefully when API key…
self-media-short-video
把已确认的母题或文案转成可直接拍摄、录屏或交给视频工具制作的短视频方案，也支持在用户确认肖像与声音权利并完成平台手动上传后制作数字人视频。用于视频号、抖音、小红书视频和其他竖屏短视频的口播稿、前 3 秒钩子、分镜、字幕、录屏清单、封面、话题、BGM 建议、数字人制片包和发布文案。.
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。.
x-marketing
Plan, draft, audit, and publish posts and threads for X (Twitter). Use when the user wants to write a single tweet or an auto-numbered thread, build a long-form tweetstorm, remove AI tells from a draft, reverse-engineer the hook from a viral tweet, draft a reply or quote tweet, or plan a week of X content. Tweets and…