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 skills add GGbond-bo/MemOmics-Agent --skill competitor-agent-researchgit clone --depth 1 https://github.com/GGbond-bo/MemOmics-AgentWrote 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/ggbond-bo/memomics-agent/competitor-agent-research)<a href="https://agentmods.dev/skills/ggbond-bo/memomics-agent/competitor-agent-research"><img src="https://agentmods.dev/badge/skills/ggbond-bo/memomics-agent/competitor-agent-research/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ggbond-bo/memomics-agent/competitor-agent-research"><img src="https://agentmods.dev/badge/skills/ggbond-bo/memomics-agent/competitor-agent-research.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00101 | $0.01360 |
| Opus 5 | $0.00051 | $0.00680 |
| Sonnet 5 | $0.00020 | $0.00272 |
| Haiku 4.5 | $0.00010 | $0.00136 |
Grade C, and why
competitor-agent-research scanned grade C with 2 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 2d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| terminal 中 rm -rf 被拦截 | 安全护栏拦截删除 | 克隆到新目录名，不要 rm 旧目录 | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
本机 git clone github.com:443 常连不上（2026-08 实测），但 **api.github.com 和 raw.githubusercontent.com 用 curl/urllib 可通**。 How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
竞品科研 AI Agent 调研
用户要求调研/对比 MemOmics 与其他科研 AI Agent（如 Biomni、BiOmics）在能力和架构上的差距。 本 skill 提供可复用调研方法论 + 已调研竞品的知识库。
触发提示: "XX 和我的差距" / "调研一下 XX" / "能力和架构" / "竞品" / "biomini" / "Biomni"
调研流程（5 步）
Step 1 — 身份确认（必做，防止音译歧义）
用户口述产品名常是模糊音译（"biomini" = Biomni）。先 web_search 中英文各一轮 + search_papers， 确认: 官方名 / 团队 / 论文(期刊+年份) / GitHub repo。拿不到准确身份前不要写对比结论。
Step 2 — GitHub API 优先（git clone 常失败）
本机 git clone github.com:443 常连不上（2026-08 实测），但 api.github.com 和 raw.githubusercontent.com 用 curl/urllib 可通。 用 Python urllib + retry 抓:
api.github.com/repos/<owner>/<repo>→ default_branch, stars, descriptionapi.github.com/repos/<owner>/<repo>/git/trees/<branch>?recursive=1→ 完整文件树（看模块划分、工具清单、协议库）raw.githubusercontent.com/<owner>/<repo>/<branch>/<path>→ 逐个拉源码文件
Step 3 — 论文 PDF 直接下载 + pypdf 提取
官方站点常有 paper.pdf。urllib 下载后 pypdf 提取全文，用关键词切片定位关键段落 （如 "150 specialized tools" / "ablation" / "outperformed"）。数字和对比结论必须从原文提取，不能凭记忆。
Step 4 — 源码结构反推架构（比读论文快）
对 agent 主文件（可能 100KB+）用 regex 提取:
class \w+→ 核心类def \w+→ 方法清单（架构特征一目了然: retriever/self_critic/plan/execute/memory/verif）- 关键词计数 → 判断机制是否存在（如 self.critic=27次 → self-critic 是核心机制）
Step 5 — 能力 vs 架构双维度对比（交付格式）
- 能力层: 对方有的我有没有（工具数/数据库数/基准成绩/任务类型/交付物）；我有的对方有没有（长任务/发表级出图/自进化/多角色辩论）
- 架构层: 环境(工具+软件+数据库) / 规划(模板驱动 vs 代码为中心) / 执行 / 质量控制 / 学习机制 / 编排框架
- 交付要求: 一句话定位差异本质（"他赢在广度和可验证，我赢在深度和落地"）→ 能力对照表 → 架构对照表 → 追赶优先级列表
- 引用来源标注（Science 论文/官网/GitHub/PubMed），用户会验证
工具陷阱（本机实测）
| 陷阱 | 现象 | 修复 |
|---|---|---|
| execute_python 的 /tmp ≠ bash 的 /tmp | execute_python 写 /tmp/xxx 后 bash ls /tmp 看不到 |
直接写显式路径（如 <安装目录>/results/<session>/）再 read_file |
| web_extract 后端不可用 | DuckDuckGo search-only 后端无法 extract URL | 用 execute_code 内 hermes_tools.web_extract 或 urllib 直接抓 |
| git clone 失败 | github.com:443 连接超时 | 改用 GitHub REST API（api.github.com 通） |
| terminal 中 rm -rf 被拦截 | 安全护栏拦截删除 | 克隆到新目录名，不要 rm 旧目录 |
Support Files
references/biomni-knowledge-bank.md— Biomni (Science 2026) 架构/基准/与 MemOmics 对比知识库
What ships with it
2 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.
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.
- 2d ago Changed 5249e5c9064c
- 9d ago First seen · 79 lines · 101 tokens per session scan C 754f496efe50
competitor-agent-research is a skill published in the GitHub repository GGbond-bo/MemOmics-Agent (19 stars, last pushed 2d ago), licensed MIT. It adds 101 tokens to every session and 1,360 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…