Individual skill
modal-serverless-gpu
Run approved CPU or GPU work through OpenScience compute_job on the user's configured Modal account. Use for isolated scientific scripts, dependency provisioning, durable outputs, logs, status, cancellation, and recovery. Never invoke the Modal SDK or CLI directly.
backend/cli/skills/cloud-compute/modal/SKILL.md
Source commit a08e0ad0ad3d6448123039ee4659163eb2e35d99
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 2, 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)
- 4,353
- 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.
- agent Repository topic
- ai Repository topic
- bun Repository topic
- cli Repository topic
- llm Repository topic
- ml Repository topic
- open-source Repository topic
- research Repository topic
- science Repository topic
- ai-agent Repository topic
- infrastructure Declared skill tag
- serverless Declared skill tag
- gpu Declared skill tag
- cloud Declared skill tag
- modal Declared skill tag
- sandboxes Declared skill tag
- compute Declared skill tag
- devops Derived category
- research Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Read excerpt
# Modal through `compute_job`
Modal is an OpenScience compute target, not an agent-controlled SDK. Prepare ordinary workspace files and call `compute_job` with target `{ kind: "modal" }`. The JobBroker owns credentials, the reviewed dispatch card, sandbox lifecycle, logs, cancellation, recovery, and output delivery.
## Contract
- Read `<compute-capability>` for the configured/disabled/unconfigured state. Do not probe availability by launching work.
- Never inspect Modal credentials or `~/.modal.toml`; never install or invoke the Modal Python SDK or CLI.
- Commands are ordinary shell commands inside `/workspace`, such as `python analysis.py`.
- The `packages` list builds Python dependencies into the reviewed image before execution. Pin important versions.
- With no `cwd`, omitted `uploads` stages safe ordinary files from session scratch. With a `cwd`, it stages from that directory. Pass explicit globs to narrow inputs; pass `uploads: []` only when the job needs no workspace files.
- Declare every output needed after the run in `artifacts`. Undeclared files are not delivered.
- Use GPU `none` for CPU work. Choose GPU count, CPU, memory, and timeout from the workload; do not invent price or duration guarantees.
- Network `none` is the safe default. Use unrestricted network only when the command genuinely needs remote access and the approval card shows it.