remote-compute-modal SKILL.md skillA

remote-compute-modal from pengqianhan/ai-human-research-os is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add pengqianhan/ai-human-research-os/remote-compute-modal@git:20260715.38d79be

Pins git:20260715.38d79be in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
pengqianhan/ai-human-research-os
Path
research-skills-hub/claude-science-skills/skills/remote-compute-modal/SKILL.md
Versions recorded
1
Latest version
git:20260715.38d79be, committed Jul 15, 2026
Size
43,964 bytes
Repository stars
3
License
MIT

Run GPU jobs on the user's own Modal account via host.compute.create('byoc:modal', ...). Covers the create→submit→wait_for_notification flow, the compute_provider kernel for env setup, image/volume resolution, and the two approval cards. Load once you've decided to dispatch to Modal.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

You're dispatching to the user's Modal account: containers spin up in Modal's
cloud, on hardware you name in plain terms (gpu/cpu/memory/timeout), under
their workspace, on their bill. That's the reason there are
two approval cards rather than one, and the reason the env-setup surface is
a separate kernel rather than something you can call inline from the
control-plane kernel: each card is the user consenting to a specific,
bounded use of their credential, and the architecture keeps those grants
legible by keeping the surfaces apart.

If `compute.create('byoc:modal', …)` returns `unknown provider 'byoc:modal'`,
Modal isn't enabled in this install — ask the user to enable it under
*Settings → Compute → Modal* (or surface the prompt; you can't enable it for
them).

For first-time environment setup, see `env-setup.md` in this skill
directory — it walks through driving the `compute_provider` kernel to
build and record images.

## Two timeouts, one timeline

Modal has two deadline timers. Both live INSIDE the sandbox, and neither
can cost you the outputs of a job that ran. The timeline every job runs
on:

1. Container life starts at sandbox creation — staging the inputs counts
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add pengqianhan/ai-human-research-os/remote-compute-modal@sha256:52e7603e2f30e4f4

The line at the top of this page pins the label git:20260715.38d79be, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_5fvdmm7unkobeduu.svg)](https://markdownregistry.com/a/art_5fvdmm7unkobeduu)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jul 15, 2026.

versioncommittedcommitsizeaudit
git:20260715.38d79be latest2026-07-15 38d79be 43,964 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (43964 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

pengqianhan/ai-human-research-os · 3 stars · license MIT · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_5fvdmm7unkobeduu
GET https://markdownregistry.com/api/v1/resolve?ref=pengqianhan/ai-human-research-os/remote-compute-modal
GET https://markdownregistry.com/api/v1/blob/52e7603e2f30e4f4b057d9a203bdf2ca9397f072801b33c9c416558a3fa08206

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from pengqianhan/ai-human-research-os

AGENTS.md AGENTS.md file
pengqianhan/ai-human-research-os · AGENTS.md
git:20260930.4bad615 · audit A · 3 stars
DESIGN.md@os-ui DESIGN.md file
pengqianhan/ai-human-research-os · os-ui/DESIGN.md
git:20261010.e6ff292 · audit A · 3 stars
DESIGN.md@os-ui/client DESIGN.md file
pengqianhan/ai-human-research-os · os-ui/client/DESIGN.md
git:20261010.365f7eb · audit B · 3 stars
AGENTS.md@projects-folder/nanochat_cpu AGENTS.md file
pengqianhan/ai-human-research-os · projects-folder/nanochat_cpu/AGENTS.md
git:20260928.63ead0b · audit A · 3 stars
AGENTS.md@projects-folder/templates/ai_research_template AGENTS.md file
pengqianhan/ai-human-research-os · projects-folder/templates/ai_research_template/AGENTS.md
git:20260928.c3acde4 · audit A · 3 stars
algorithmic-art SKILL.md skill
pengqianhan/ai-human-research-os · research-skills-hub/claude-science-skills/skills/algorithmic-art/SKILL.md · Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users…
git:20260715.38d79be · audit B · 3 stars
alphafold2 SKILL.md skill
pengqianhan/ai-human-research-os · research-skills-hub/claude-science-skills/skills/alphafold2/SKILL.md · Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al. 2022…
git:20260715.38d79be · audit A · 3 stars
boltz SKILL.md skill
pengqianhan/ai-human-research-os · research-skills-hub/claude-science-skills/skills/boltz/SKILL.md · Structure prediction for protein, nucleic-acid, and small-molecule complexes with Boltz-2 (Passaro & Wohlwend et al…
git:20260715.38d79be · audit A · 3 stars
borzoi SKILL.md skill
pengqianhan/ai-human-research-os · research-skills-hub/claude-science-skills/skills/borzoi/SKILL.md · Predict genome-wide functional tracks (RNA-seq, CAGE, DNase, ChIP) from DNA sequence with Borzoi. Use this skill when…
git:20260715.38d79be · audit A · 3 stars
chai1 SKILL.md skill
pengqianhan/ai-human-research-os · research-skills-hub/claude-science-skills/skills/chai1/SKILL.md · Structure prediction for protein, nucleic-acid, and small-molecule complexes with the Chai-1 foundation model (Chai…
git:20260715.38d79be · audit A · 3 stars
compute-env-setup SKILL.md skill
pengqianhan/ai-human-research-os · research-skills-hub/claude-science-skills/skills/compute-env-setup/SKILL.md · Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts…
git:20260715.38d79be · audit A · 3 stars
customize SKILL.md skill
pengqianhan/ai-human-research-os · research-skills-hub/claude-science-skills/skills/customize/SKILL.md · Create, configure, and maintain custom agent profiles and author new skills via the `repl` tool. Use when the user…
git:20260715.38d79be · audit B · 3 stars

Every file in pengqianhan/ai-human-research-os

Browse by kind, by grade A, or by owner.