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 poplarity/dsh-science-workbench --skill bio-workbenchgit clone --depth 1 https://github.com/poplarity/dsh-science-workbenchWrote 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/poplarity/dsh-science-workbench/bio-workbench)<a href="https://agentmods.dev/skills/poplarity/dsh-science-workbench/bio-workbench"><img src="https://agentmods.dev/badge/skills/poplarity/dsh-science-workbench/bio-workbench/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/poplarity/dsh-science-workbench/bio-workbench"><img src="https://agentmods.dev/badge/skills/poplarity/dsh-science-workbench/bio-workbench.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 | $0.00116 | $0.01619 |
| Opus 5 | $0.00058 | $0.00809 |
| Sonnet 5 | $0.00023 | $0.00324 |
| Haiku 4.5 | $0.00012 | $0.00162 |
Grade A, and why
bio-workbench 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 10d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
生信分析工作台约定(dsh-science-workbench)
这是 agent 在执行生信分析时必须遵守的约定。核心原则:每个产物都可溯源、可重放——回答"这张图 = 哪段代码 + 哪些输入 + 什么环境 + 什么参数/种子",并能重跑。
1. 项目布局
每个分析项目是一个目录,结构固定:
<workspace>/bio-projects/<name>/
├─ manifest.json # 唯一事实来源(账本):cells + artifacts + provenance + 反馈
├─ environment.lock # 环境快照(interpreter 版本 + pip freeze)
├─ code/ # 每个 cell 一个自包含脚本 cell_0001.py / cell_0001_v2.py ...
├─ data/ # 输入数据(引用或副本)
├─ figures/ # 图产物(.png 等,可配 .data.tsv 原始绘图数据)
└─ .git/ # 项目自动 git(每次 cell 跑完/反馈 自动本地 commit,不 push)
2. cell 契约(脚本头声明块)
每个 cell 脚本顶部有一段由工具生成的声明头,声明即契约:
# @cell: cell_0001
# @title: TSS profile
# @language: python
# @seed: 42
# @params: {"bin": 50, "upstream": 3000}
# @inputs: ["data/peaks.bed"]
# @outputs: ["figures/tss_profile.png"]
规则:
- 图必须写到
figures/下(相对项目根路径),这样运行后能自动被发现并登记 provenance。 - 非图的中间产物(tsv/csv/bed 等)通过
outputs显式声明。 - 脚本要自包含:显式读输入、写输出;cwd = 项目根;用相对路径。
3. manifest 记账(唯一事实来源)
{
"schemaVersion": 1,
"name": "...", "root": "...",
"environment": {"language": "python", "interpreter": "3.12.x", "lockFile": "environment.lock"},
"cells": [ { "id", "title", "script", "language", "params", "seed", "inputs",
"status": "ok|error", "artifacts": [], "ranAt", "stdoutTail", "stderrTail", "derivedFrom" } ],
"artifacts": [ { "path", "kind": "figure|data|file", "producedBy", "inputHashes",
"outputHash", "params", "seed", "env", "createdAt", "feedback": [], "derivedFrom" } ]
}
- 每个 artifact 的
outputHash与每个inputHashes都是 SHA-256,保证可复现性证据。 feedback挂在 artifact 上;derivedFrom记录版本派生关系(v1 → v2)。
4. 出图 → 反馈 → 重画循环
- 出图:调用
bio_run_cell(含title+code+params+seed+inputs)。 - 视觉自检(Tier 0,默认):程序化检查——渲染是否成功(exit code)、是否有图产出、dpi/尺寸合理性。人(用户)是默认的眼睛:图永远先给用户看。
- 反馈:用户对图提出反馈("改 x 轴 / 换配色 / 加 p 值"),用
bio_add_feedback把反馈作为结构化记录挂到对应 artifact 上(进 manifest + git commit)。 - 重画:调用
bio_rerun_cell(cellId+editedCode),生成版本化新 cell(cell_0001_v2),重跑、重新发现图、登记新 artifact 并记录derivedFrom派生关系。
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.
- 10d ago First seen · 96 lines · 116 tokens per session scan A 2c3254267fa2
bio-workbench is a skill published in the GitHub repository poplarity/dsh-science-workbench (9 stars, last pushed 14d ago), licensed MIT. It adds 116 tokens to every session and 1,619 once invoked, about $0.0006 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
structure-prediction
Protein structure prediction from sequence. ESMFold-based, single GPU, no MSA needed. Predicts 3D structures with pLDDT confidence scores for drug discovery targets.
ito-inference
Inspect the availability of model serving on a completed Itô compute booking and, when the canonical backend becomes available, hand off an explicitly confirmed serving manifest. Use after ito-compute has booked GPU nodes and the user asks for an OpenAI-compatible endpoint, ito-serve, hosted Kimi, or self-hosted…
ito-training
Inspect the availability of ML training on a completed Itô compute booking and, when the canonical backend becomes available, hand off an explicitly confirmed training manifest. Use after ito-compute has booked GPU nodes and the user wants pre-training, fine-tuning, or RL on that metal. ECC implements no training…
ito-compute
Query live GPU inventory, submit an authenticated Itô fixed-rate RFQ, inspect RFQ or procurement status, revoke device credentials, and run explicitly gated node qualification through the separately installed canonical CLI. Use when a user asks to find H100/H200 capacity, request a fixed compute rate, check Itô…
Jupyter Live Kernel
Guides notebook-first analysis with reproducible kernels, inspectable data loading, and explicit promotion paths back into durable code.
ehr-analysis
End-to-end EHR predictive modeling pipeline with PyHealth, covering dataset loading, task definition, model training, evaluation, calibration, and clinical interpretation.