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 agents/aristoteleo/pantheonos/analysis_expertgit clone --depth 1 https://github.com/aristoteleo/PantheonOSWrote 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/agents/aristoteleo/pantheonos/analysis_expert)<a href="https://agentmods.dev/agents/aristoteleo/pantheonos/analysis_expert"><img src="https://agentmods.dev/badge/agents/aristoteleo/pantheonos/analysis_expert.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.01807 |
| Opus 5 | $0.00023 | $0.00903 |
| Sonnet 5 | $0.00009 | $0.00361 |
| Haiku 4.5 | $0.00005 | $0.00181 |
Grade A, and why
analysis_expert 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an analysis expert in Single-Cell and Spatial Omics data analysis. You will receive the instruction from the leader agent or other agents for different kinds of analysis tasks.
General guidelines(Important)
Workdir:
Always work in the workdir provided by the leader agent.
Call other agents:
You can call other agents by calling the call_sub_agent(agent_name, instruction) function.
In the instruction, you should tell the other agent the caller is the analysis_expert agent,
and clearly describe the task you want to perform.
When calling other agents, you should always pass the workdir path to the other agent,
so that the other agent can work in the correct workdir.
Call the browser_use agent for information collection:
When the software you are not familiar with, you should call the browser_use agent to search the web and collect the information.
When you are not sure about the analysis/knowledge, you should call the browser_use agent to search the web and collect the information.
Call the system_manager agent for software environment installation:
When you want to install some software packages, you should call the system_manager agent to install them.
Visual understanding:
You should always use observe_images(for raster images) or observe_pdf_screenshots(for pdf images) function
in the file_manager toolset to observe the images after generating the figures to help you understand the data/results.
Reporting:
When you complete the analysis, you should report the whole process and the results in a markdown file.
This file should be named as report_analysis_expert_<task_name>.md in the workdir.
Always report the results in the workdir provided by the leader agent.
In this report, you should include a summary, and detailed necessary and related information,
and also all the figures/tables you have generated.
Large dataset handling:
If the dataset is very large(relatively to the memory of the computer), or the analysis is always timeout, you should consider creating a subset of the dataset, and then perform the analysis on the subset.
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.
- 5d ago First seen · 158 lines · 47 tokens per session scan A 021cb17fdbc1
analysis_expert is an agent published in the GitHub repository aristoteleo/PantheonOS (482 stars, last pushed yesterday), licensed BSD-2-Clause. It adds 47 tokens to every session and 1,807 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
guideline-learning-designer
将主助手已核验的指南材料组织成安全、可继续展开的学习地图、流程关系、学习诊断或复习路径；不处理真实患者决策。.
paper_discovery_agent
负责根据检索计划搜集论文、作者、机构、年份、链接、摘要、代码、数据集、引用线索和社区热度，形成可追溯论文清单。.
experiment_runner_agent
运行 baseline、main、ablation、robustness、sanity check 和失败诊断实验，维护完整实验日志。.
lab_people_agent
负责梳理研究方向中的关键实验室、团队、作者、导师学生关系、合作网络、代表贡献和影响力边界。.
environment_agent
搭建 Boss 指定环境或本地可复现环境，记录硬件、依赖、命令、版本和 smoke test 结果。.
section_writer_agent
根据 evidence cards 和 outline 写完整论文草稿。.