agentmods.dev

external-repo-setup

external-repo-setup is a skill for Claude Code, Codex from mims-harvard/AutoScientists. It costs 65 tokens per session (5,031 once invoked), scanned A, original, no licence file.

A setup procedure for bringing an outside GitHub repository and its pretrained model files into a GPU-based machine-learning project. A pretrained model is one that has already been trained on data.

In plain words
What is it for?
Use it to clone repositories, install dependencies, download model weights, and connect them to a focus area's training script.
Why use it?
It provides a defined process when a project depends on code or model files that are not already in the workspace.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

not rated 792repo +2 22d ago A scan 65 tokens no licence

Good fit Use it to clone repositories, install dependencies, download model weights, and connect them to a focus area's training script.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mims-harvard/autoscientists/external-repo-setup
View source ↗ mims-harvard/AutoScientists autoscientists.openscientist.ai
Install

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.

Any agent
npx skills add mims-harvard/AutoScientists --skill external-repo-setup
Clone the repo
git clone --depth 1 https://github.com/mims-harvard/AutoScientists

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for external-repo-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/mims-harvard/autoscientists/external-repo-setup/github.svg)](https://agentmods.dev/skills/mims-harvard/autoscientists/external-repo-setup)
Your own site
<a href="https://agentmods.dev/skills/mims-harvard/autoscientists/external-repo-setup"><img src="https://agentmods.dev/badge/skills/mims-harvard/autoscientists/external-repo-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.

agentmods 80×15 button for external-repo-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/mims-harvard/autoscientists/external-repo-setup"><img src="https://agentmods.dev/badge/skills/mims-harvard/autoscientists/external-repo-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,031 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.05031
Opus 5.5 $0.00026 $0.02012
Sonnet 5.5 $0.00013 $0.01006
Haiku 4.5 $0.00006 $0.00503

Measured 2mo ago against content hash 509e4480dfb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

external-repo-setup scanned grade A 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

import urllib.request, hashlib

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

subprocess.run(
system/external-repo-setup/SKILL.md · 531 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Files

What ships with it

1 file 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.

Changes

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.

  1. 2mo ago First seen · 531 lines · 65 tokens per session scan A 509e4480dfb3

Subscribe to this mod's changes

external-repo-setup is a skill published in the GitHub repository mims-harvard/AutoScientists (792 stars, last pushed 22d ago), with no licence file. It adds 65 tokens to every session and 5,031 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AIagentsai-for-scienceai-scientistslong-running-agentsself-evolving-agentsself-organizing
Related

external-repo-setup compared with skills from other repositories

external-repo-setup next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
external-repo-setupmims-harvard/AutoScientistsSkill79222d agononeA65Claude Code, Codex
tooluniverse-single-cellmims-harvard/ToolUniverseSkill1.8kyesterdayApache-2.0A146Claude Code
tooluniverse-protein-structure-predictionmims-harvard/ToolUniverseSkill1.8kyesterdayApache-2.0A71Claude Code
tooluniverse-ml-inference-utilitymims-harvard/ToolUniverseSkill1.8kyesterdayApache-2.0A0Claude Code
tooluniverse-protein-sae-variant-interpretationmims-harvard/ToolUniverseSkill1.8kyesterdayApache-2.0A144Claude Code
tooluniverse-proteomics-analysismims-harvard/ToolUniverseSkill1.8kyesterdayApache-2.0A76Claude Code
tooluniverse-spatial-omics-analysismims-harvard/ToolUniverseSkill1.8kyesterdayApache-2.0A97Claude Code