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/vibhasdutta/loop-engineer/opencodenpx skills add vibhasdutta/loop-engineer --skill opencodegit clone --depth 1 https://github.com/vibhasdutta/loop-engineerWhat 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 | $0.02995 |
| Opus 5 | $0.00051 | $0.01497 |
| Sonnet 5 | $0.00020 | $0.00599 |
| Haiku 4.5 | $0.00010 | $0.00299 |
Grade A, and why
loop-engineer 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
43 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- AGENTS.md 1.9 KB
- agents/agent-factory.md 2.2 KB
- agents/auditor.md 2.2 KB
- agents/executor.md 2.9 KB
- agents/knowledge-sources.md 6.4 KB
- agents/knowledge-sources/01-search-engines.md 237 B
- agents/knowledge-sources/02-open-source-code.md 255 B
- agents/knowledge-sources/03-official-documentation.md 460 B
- agents/knowledge-sources/04-package-managers.md 258 B
- agents/knowledge-sources/05-research-papers.md 336 B
- agents/knowledge-sources/06-ai-machine-learning.md 322 B
- agents/knowledge-sources/07-apis.md 144 B
- agents/knowledge-sources/08-community-discussions.md 271 B
- agents/knowledge-sources/09-tutorials-learning.md 245 B
- agents/knowledge-sources/10-cybersecurity.md 210 B
- agents/knowledge-sources/11-system-design.md 181 B
- agents/knowledge-sources/12-business-startups.md 220 B
- agents/knowledge-sources/13-marketing.md 152 B
- agents/knowledge-sources/14-sales-lead-generation.md 246 B
- agents/knowledge-sources/15-jobs-careers.md 145 B
- agents/knowledge-sources/16-design.md 190 B
- agents/knowledge-sources/17-images.md 124 B
- agents/knowledge-sources/18-videos.md 125 B
- agents/knowledge-sources/19-books.md 127 B
- agents/knowledge-sources/20-news.md 149 B
- agents/knowledge-sources/21-government.md 156 B
- agents/knowledge-sources/22-finance.md 153 B
- agents/knowledge-sources/23-legal.md 112 B
- agents/knowledge-sources/24-medical.md 82 B
- agents/knowledge-sources/25-science.md 99 B
- agents/knowledge-sources/26-geography.md 87 B
- agents/knowledge-sources/27-shopping.md 119 B
- agents/knowledge-sources/28-social-media.md 194 B
- agents/knowledge-sources/29-wikis.md 103 B
- agents/knowledge-sources/30-domain-website-intelligence.md 295 B
- agents/knowledge-sources/31-datasets.md 159 B
- agents/knowledge-sources/32-file-types.md 270 B
- agents/knowledge-sources/33-browser-capabilities.md 461 B
- agents/memory-keeper.md 1.8 KB
- agents/planner.md 1.9 KB
- agents/researcher.md 6.1 KB
- agents/resource-scout.md 4.0 KB
- commands/loop-engineer.md 295 B
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 · 225 lines · 102 tokens per session scan A e99b0b286e1c
loop-engineer is a skill published in the GitHub repository vibhasdutta/loop-engineer (3 stars, last pushed 1mo ago), with no licence file. It adds 102 tokens to every session and 2,995 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
intelligent-content-system
内容创作者与运营专员在需要采集网页、追踪热点或进行多平台分发时，使用此技能可一键完成从内容获取、智能配图、小红书图文生成到微信、小红书、X、B站等多平台自动发布的全流程，轻松实现内容产出与分发效率翻倍。 智能内容创作与发布全流程系统。根据用户需求自动识别场景， 编排调用网页采集、智能配图、小红书图文生成、热点内容创作、多平台发布等技能， 实现从内容获取到发布的一站式自动化。 支持场景： - 网页内容采集与再创作（采集→配图→发布） - 热点内容创作（热点采集→AI生成→多平台发布） - 原创内容优化（配图→小红书图文→发布） - 单一功能调用（采集/配图/图文/发布） 支持平台：微信公众号、小红书、X/Twitter、B站.
obsidian-bases
内容创作者与技术写作员在管理海量笔记时，当需要构建 Obsidian 数据库视图、配置过滤器或编写 YAML 公式，使用此技能可自动生成标准 .base 文件，轻松实现笔记的表格/卡片多维展示与数据汇总，让知识库管理效率翻倍。.
product-marketing-copywriter
当市场调研分析师与营销专员、内容创作者需要推广产品时，使用本技能可精准分析受众痛点与产品卖点，一键生成高转化标题与正文，快速产出激发购买欲的优质营销文案，大幅提升销售转化率。.
baoyu-post-to-wechat
自媒体创作者与运营专员在需要将 Markdown 或 HTML 内容发布至微信公众号时，一键通过 API 或浏览器自动化完成文章与图文的排版及发布，彻底告别繁琐的手动排版与多步上传操作，大幅提升公众号日常发文与运营效率。.
content-research-writer
内容创作者、技术写作员在撰写博客、深度文章或技术文档时，使用此技能可开启全流程写作协作。它能帮你研究资料、构建大纲、逐段打磨并自动添加引用，快速优化Hook，让你高效产出高质量内容，告别孤军奋战！.
dream-video-prompt-generator
电商运营与内容创作者在制作数字人带货短视频时，用本技能一键生成即梦视频中英文提示词。依托四大智能体协同与专属公式，确保人物与情绪高度一致，完美适配5s带货场景，高效产出高质量分镜脚本，让视频制作事半功倍！.