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 clinicaltrials-landscapegit 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/clinicaltrials-landscape)<a href="https://agentmods.dev/skills/ggbond-bo/memomics-agent/clinicaltrials-landscape"><img src="https://agentmods.dev/badge/skills/ggbond-bo/memomics-agent/clinicaltrials-landscape/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/clinicaltrials-landscape"><img src="https://agentmods.dev/badge/skills/ggbond-bo/memomics-agent/clinicaltrials-landscape.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 | $0.00005 | $0.04481 |
| Opus 5 | $0.00003 | $0.02240 |
| Sonnet 5 | $0.00001 | $0.00896 |
| Haiku 4.5 | $0.00001 | $0.00448 |
Grade A, and why
clinicaltrials-landscape 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 9d 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.
This is a copy
95% identical to ClinicalTrials.gov Disease Landscape Scanner — 625 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⛔ MemOmics 强制规则（不可违反，优先级最高）
本 skill 已集成到 MemOmics-Agent 自进化生信分析平台。以下规则覆盖所有 Biomni 默认行为。
规则1: 拿到数据 → 必须调 search_knowledge
- 每个分析步骤写代码前，必须先调
search_knowledge(species=..., tissue=..., direction=..., query="<步骤名> 参数") - 知识库有匹配 → 用知识库的参数和模板
- 知识库无匹配 → 用 web 搜索文献，提取方法和参数，存入知识库
- 绝对不能跳过直接写代码
规则2: 7步循环（每步必须走完整循环）
1. search_knowledge 查本步骤的方法和参数
2. check_env 检查环境
3. rail_review(pre) 前置审查
4. source/import 预写脚本（禁止 inline 代码）
5. terminal 执行（分步执行，禁止 && 连接多步骤）
6. debate_analysis 多方辩论（正方/反方切断上下文独立生成 + LLM裁决）
7. rail_review(post) 后置审查
规则3: 代码分段执行 — 写一步跑一步
- ❌ 禁止一次性写完全部代码用 && 连接执行
- ✅ 必须分步：写一步 → 执行 → 检查结果 → 辩论 → 下一步
规则4: 关键参数多参数尝试 + 辩论
- 涉及数值参数时（如 resolution, n_pcs, min_features, FDR threshold等），至少尝试 2-3 个值
- 每次参数变更后调
debate_analysis辩论"这个参数合理吗？结果有没有变好？" - 辩论格式（多角色对抗 v3）：
- 正方 3 位专业编辑（各自独立，互相不知道）：生物学编辑 / 统计学编辑 / 生信编辑
- 反方 4 位专业编辑（各自独立，互相不知道，也看不到正方）：生物学编辑 / 统计学编辑 / 生信编辑 / 历史经验编辑
- 裁判编辑：看到所有 7 方论点，给出裁决 + 置信度（高/中/低）
- 上下文隔离：每个编辑独立 HTTP API 调用，messages 只有自己的 prompt
- 分科知识库：生物学编辑用 biology_kb / 统计学编辑用 statistics_kb / 生信编辑用 bioinfo_kb / 历史经验编辑用 history_errors
- 辩论结果自动归档到 results/.../log/debate_*.json
- 不确定的参数就辩论，不要自己拍脑袋
规则5: 执行后审查
规则N: 运行记录只是参考，不能跳过审查
-
skill_evolution(action="query_logs") 返回的历史运行日志仅供参数参考
-
即使有 quality_score=9.0 的历史日志，仍必须执行 rail_review(pre)、debate_analysis、rail_review(post)
-
禁止因"之前跑过"而跳过任何审查步骤
-
禁止直接用历史日志里的脚本运行而不经本次审查
-
运行日志是"参考"不是"免审凭证"
- 图片检查：
- 图有没有生成？没生成 → 强制重新执行
- 图片是否空白（全白/全黑/全单一色）？空白 → 强制重新出图
- 图片是否有 NA/缺失值（>10% 像素是 NA）？有 NA → 强制重新出图
- 图片大小是否过小（<5KB）？过小 → 强制重新出图
- 图片数量是否足够？（每步至少 1 张图，关键步骤至少 2-3 张）
- 代码质量检查：
- 代码行数是否合理？（过短可能偷懒，过长可能未分段）
- 代码是否有注释？
- 代码是否分段执行（禁止 && 连接多步骤）？
- 结果合理性：
- 数值范围是否合理？
- 跟知识库对应吗？
- 参数和结论辩论：
- 有参数的选择 → 必须调 debate_analysis 辩论
- 有结论输出 → 必须调 debate_analysis 辩论
- 不通过 → 修复重跑
- 通过 → 必须调 skill_evolution(action="record_run") 记录成功经验（skill_name/script_name/species/tissue/direction/params_used/result_summary/quality_score/notes） → 创建目录存储(figures/results/scripts/data) → 下一步
- 不通过 → 修复后重跑 → 成功后调 skill_evolution(action="record_run")；如果是脚本报错 → 调 skill_evolution(action="record_error") 记录根因+修复方案
- 图片检查：
What ships with it
15 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.
- .gitignore 305 B
- references/api-parameters.md 5.7 KB
- references/mechanisms.md 4.9 KB
- references/output-schema.md 7.4 KB
- scripts/__init__.py 732 B runs code
- scripts/classify_mechanisms.py 13 KB runs code
- scripts/compile_trials.py 24 KB runs code
- scripts/disease_config.py 5.5 KB runs code
- scripts/export_all.py 10 KB runs code
- scripts/generate_landscape_plots.py 27 KB runs code
- scripts/generate_pdf_report.py 64 KB runs code
- scripts/generate_report.py 84 KB runs code
- scripts/query_clinicaltrials.py 11 KB runs code
- scripts/run.py 1.8 KB runs code
- skill.json 972 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.
- 9d ago First seen · 364 lines · 5 tokens per session scan A 3a5c1d37eaa6
clinicaltrials-landscape is a skill published in the GitHub repository GGbond-bo/MemOmics-Agent (19 stars, last pushed 2d ago), licensed MIT. It adds 5 tokens to every session and 4,481 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to ClinicalTrials.gov Disease Landscape Scanner, differing in 625 lines, and is treated as a copy.
Other skills, from other repositories
bulkrna-survival
Load when stratifying patients by gene expression and testing for survival differences (Kaplan-Meier + Cox) in bulk RNA-seq. Skip when no time-to-event clinical data exists; non-bulk cohorts (single-cell / spatial survival is not supported).
clinical-research-analysis-framework
Guided workflow for statistical and ML analysis of clinical data. Use when planning or executing research analyses on MIMIC, eICU, or similar EHR data. Ensures methodological rigor through structured consultation, assumption checking, and stepwise execution with audit trails.
apache-iv-score
Calculate APACHE IV (Acute Physiology and Chronic Health Evaluation IV) score for ICU mortality prediction. Use for severity assessment, hospital mortality prediction, ICU benchmarking, or case-mix adjustment. eICU has pre-computed scores; MIMIC-IV requires custom implementation with diagnosis mapping challenges.
oasis-score
Calculate OASIS (Oxford Acute Severity of Illness Score) for ICU patients. Use for mortality prediction with fewer variables than APACHE/SAPS, or when lab data is limited.
clinical-research-pitfalls
Avoid common methodological mistakes in clinical research with EHR databases. Covers immortal time bias, information leakage, selection bias, and other critical pitfalls.
sapsii-score
Calculate SAPS-II (Simplified Acute Physiology Score II) for ICU patients. Use for mortality prediction, severity assessment, or international ICU benchmarking.