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/performance-optimizernpx skills add moses607/socialforge --skill performance-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 | $0.00093 | $0.01112 |
| Opus 5 | $0.00046 | $0.00556 |
| Sonnet 5 | $0.00019 | $0.00222 |
| Haiku 4.5 | $0.00009 | $0.00111 |
Grade A, and why
performance-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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Optimizer
A post that flopped is a free experiment — but only if you extract one lesson and ship the next test. Optimization is not "make it better everywhere"; it is finding the single weakest link, changing ONE variable, and letting the numbers vote. Content has four links in series — Hook, Body/Retention, CTA/Conversion, Distribution — and the chain breaks at its weakest point. Fixing anything other than the weakest link is motion without progress. Winners are not luck to admire; they are formats to industrialize. Every result routes to one of three verbs: KILL, ITERATE, or SCALE.
1. Post-mortem — isolate the weakest link
- Pull the funnel: hook rate, retention/avg watch, saves+shares per view, follows-per-view, reach.
- Find the FIRST metric below the account's median — that is the weakest link. Attribute the outcome to it, not to a vibe.
- Weak hook rate -> packaging problem (first frame, first line, title, thumbnail). Good hook + retention cliff -> body problem (pacing, payoff, structure). Good retention + low saves/follows -> CTA/value problem. Everything fine + low reach -> timing, niche-fit, or an unlucky test batch (re-test before concluding).
- State ONE root cause in a sentence. If you can't, you're guessing — get more data.
2. Design single-variable A/B tests
- Change exactly ONE variable per test so the result is attributable. Multi-variable "improvements" teach nothing.
- Highest-leverage variables in order: hook line, first frame/thumbnail, first 3 seconds, format/structure, topic angle, CTA, length, posting time.
- Write the hypothesis as: "If I change [X], then [metric] improves, because [reason]." Keep everything else identical.
- Run 3-5 posts per variant before judging — a single post is noise; the algorithm's test audience varies wildly.
- Judge on the diagnostic RATE tied to the change (hook test -> hook rate), not on total views.
3. Double-down, and decide KILL / ITERATE / SCALE
- Double-down rule: when a post beats your median by ~2-3x, immediately make 3 more in the same format/angle/hook pattern while it's hot. Winners cluster.
- KILL: below median on hook AND value after 3+ attempts — the concept doesn't land. Stop; free the slots.
- ITERATE: mixed signals (strong hook, weak body, or vice versa) — keep the strong link, run one test on the weak link.
- SCALE: clear winner — replicate the pattern, vary only surface topics, and push volume. Turn the one-off into a series/template.
- Iteration loop: Ship -> read the one weakest link -> change one variable -> re-ship -> compare to median -> route to Kill/Iterate/Scale. Repeat weekly.
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 · 68 lines · 93 tokens per session scan A a8841d5a9fb7
performance-optimizer is a skill published in the GitHub repository moses607/socialforge (2 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 1,112 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-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"…
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。.