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 BingHanOfUESTC/open_agent_team --skill reproducible-code-data-setupgit clone --depth 1 https://github.com/BingHanOfUESTC/open_agent_teamWrote 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/binghanofuestc/open_agent_team/reproducible-code-data-setup)<a href="https://agentmods.dev/skills/binghanofuestc/open_agent_team/reproducible-code-data-setup"><img src="https://agentmods.dev/badge/skills/binghanofuestc/open_agent_team/reproducible-code-data-setup/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/binghanofuestc/open_agent_team/reproducible-code-data-setup"><img src="https://agentmods.dev/badge/skills/binghanofuestc/open_agent_team/reproducible-code-data-setup.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 | $0.00036 | $0.00394 |
| Opus 5.5 | $0.00014 | $0.00158 |
| Sonnet 5.5 | $0.00007 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
reproducible-code-data-setup 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 1mo 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.
What it actually says
Reproducible Code Data Setup
This skill controls the handoff from idea to runnable research artifact.
1. Source Intake
Before using external code or data, record:
name
URL
local path
commit/tag/version
license
download date
intended use
security notes
Write it to:
research_workspace/06_code_data_manifest.md
Do not run installer scripts from unknown repositories before reading them.
2. Safety Review
Check for:
credential access
network exfiltration
destructive filesystem operations
hidden downloads
opaque binaries
postinstall hooks
unbounded subprocess spawning
license incompatibility
dataset terms that prohibit the intended use
If risk is unclear, isolate in a container or do static review only.
3. Environment Contract
Create one of:
environment.yml
requirements.txt
pyproject.toml
Dockerfile
setup_notes.md
Record:
OS
Python version
CUDA/ROCm/CPU status
GPU model and memory
package manager
exact install commands
known incompatibilities
4. Smoke Tests
Run the cheapest possible checks first:
import test
CLI help command
unit test subset
dataset sample load
one batch forward pass
one batch train step
metric computation on tiny output
Only after smoke tests pass should full experiments begin.
5. Patch Discipline
When modifying third-party code:
keep changes minimal
prefer config switches over invasive edits
document every modified file
preserve upstream license headers
separate baseline from new method
make experiment commands reproducible
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.
- 1mo ago First seen · 114 lines · 36 tokens per session scan A 001a1c47e526
reproducible-code-data-setup is a skill published in the GitHub repository BingHanOfUESTC/open_agent_team (106 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 394 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
genomic-intelligence
Predict regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no local GPU or model weights. Six tasks over a REST API and a hosted MCP server (keyless public demo): promoter regions, splice donor/acceptor sites, enhancer…
flow-cytometry-analysis
Complete flow cytometry analysis pipeline. FCS file handling, compensation, manual/automated gating, immunophenotyping, CFSE proliferation analysis, cell cycle analysis (Dean-Jett-Fox), and apoptosis assays. Extends flowio with analytical workflows. For raw FCS parsing only use flowio.
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…
cellxgene-census
Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.
rowan
Cloud-based quantum chemistry platform with Python API. Preferred for computational chemistry workflows including pKa prediction, geometry optimization, conformer searching, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2). Use when tasks involve…