Individual skill
remote-compute-modal
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.
configs/microservice/bff-service/configs/agent-skills/claude-science/remote-compute-modal/SKILL.md
Source commit 3f908c703fd75033217ed549f1998563d13a1dc0
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 9, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 2,386
- Repository last updated
- Nov 6, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai Repository topic
- llm Repository topic
- mcp Repository topic
- rag Repository topic
- wanwu Repository topic
- workflow Repository topic
- agentic-ai Repository topic
- agentic-framework Repository topic
- ai-agent Repository topic
- ai-agent-development-framework Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
.catalog_stampruns · 13 bytesSKILL.mdcore · 43,964 bytesSKILL.mdcore · 43,964 bytesSKILL.mdcore · 43,964 bytesSKILL.mdcore · 43,964 bytesSKILL.mdcore · 43,964 bytesSKILL.mdcore · 43,964 bytesSKILL.mdcore · 43,964 bytesSKILL.mdcore · 43,964 bytesSKILL.mdcore · 43,964 bytesSKILL.mdcore · 43,964 bytesSKILL.mdcore · 43,964 bytesSKILL.mdcore · 43,964 bytesSKILL.mdcore · 43,964 bytesSKILL.mdcore · 43,964 bytesSKILL.mdcore · 43,964 bytesSKILL.mdcore · 43,964 bytesSKILL.mdcore · 43,964 bytesenv-setup.mdruns · 14,431 bytesenvs/chemistry_gpu.pyruns · 1,080 bytesenvs/esmfold2_gpu.pyruns · 7,122 bytesenvs/genomics_evo2_gpu.pyruns · 2,968 bytesenvs/proteomics_boltz_gpu.pyruns · 2,272 bytesenvs/proteomics_gpu.pyruns · 3,198 bytesenvs/proteomics_jax_gpu.pyruns · 2,782 bytesenvs/proteomics_openfold_gpu.pyruns · 5,218 bytesenvs/proteomics_rfd_diffdock_gpu.pyruns · 5,144 bytesenvs/singlecell_gpu.pyruns · 4,564 bytesprovider.jsonruns · 409 bytesprovider.pyruns · 39,816 bytesrequirements.lockruns · 72,112 bytes
Read excerpt
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).