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 agentmods add skills/fmind/dot/colabnpx skills add fmind/dot --skill colabgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/colab)<a href="https://agentmods.dev/skills/fmind/dot/colab"><img src="https://agentmods.dev/badge/skills/fmind/dot/colab.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.00748 |
| Opus 5 | $0.00021 | $0.00374 |
| Sonnet 5 | $0.00008 | $0.00150 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
colab 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Colab CLI
Use colab when a task needs an accelerator the workstation lacks. The official Colab skill documents every command; this skill owns authentication, session hygiene, and the spend boundary.
Workflow
-
Authenticate: OAuth by default (
--auth oauth2), or--auth adcto reuse the Application Default Credentials from gcloud; session state lives under~/.config/colab-cli/. -
Prefer ephemeral runs:
colab runrents a VM, runs the script, and releases it; a shebang#!/usr/bin/env -S colab run --gpu T4makes a single file self-contained per python-script.colab run --gpu T4 --timeout 3600 train.py -
Keep a session only while iterating:
colab new -s <name> --gpu L4(or--tpu v6e1), thencolab exec -s <name> -f snippet.py --timeout 600,colab upload,colab download, andcolab ls. -
Stop what you started:
colab sessionsthencolab stop -s <name>; an idle session keeps consuming compute units. Runcolab statusbefore claiming a job finished. -
Verify:
colab logshows the history; download the artifacts before stopping the session.
Gotchas
- 30-second default:
colab runandcolab execabort code execution after 30 seconds unless--timeout <seconds>covers the whole job. - Pinned dependency: mise installs
google-colab-cliwithjupyter-kernel-client==0.15.0; 1.0.0 renamed the client class and breaks every session. - Tiers: accelerator availability depends on the subscription;
colab payopens the compute-units page, so treat it as spend. - Disposable VM: keep secrets off the session beyond what the task needs; use
colab drivemountonly when Drive data is required.
Official Skills
Upstream: googlecolab/google-colab-cli (the same text colab skill prints). List the current release, then install what the task needs at project scope after reviewing the snapshot (see agent-skills):
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.
- yesterday First seen · 49 lines · 42 tokens per session scan A 3d954f703ab4
colab is a skill published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 748 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other skills, from other repositories
go-stack
Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.
python-stack
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.
k8s-local
Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.
release
Cut or verify a versioned release — bump semver, generate the changelog with git-cliff, tag and publish on GitHub, or reconcile an already-published tag and assets.
chezmoi
Manage chezmoi dotfiles: source naming, Go templates, age-encrypted secrets, and the edit-source then apply/diff workflow.
cloud-run
Deploy container services to Google Cloud Run with Artifact Registry, keyless CI identity, Secret Manager, ko, or Dockerfiles.