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/swm-gpu/swm/swm-gpu-workflownpx skills add swm-gpu/swm --skill swm-gpu-workflowgit clone --depth 1 https://github.com/swm-gpu/swmWrote 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/swm-gpu/swm/swm-gpu-workflow)<a href="https://agentmods.dev/skills/swm-gpu/swm/swm-gpu-workflow"><img src="https://agentmods.dev/badge/skills/swm-gpu/swm/swm-gpu-workflow.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 | $0.00116 | $0.05803 |
| Opus 5 | $0.00058 | $0.02901 |
| Sonnet 5 | $0.00023 | $0.01161 |
| Haiku 4.5 | $0.00012 | $0.00580 |
Grade A, and why
swm-gpu-workflow 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 4d 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.
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 — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
swm — Cloud GPU Workflow Manager
One CLI to search, provision, install, sync, and tear down GPU pods across 10 cloud providers. Why swm over ad-hoc SSH scripts:
- Cross-provider search —
swm gpushits 10 providers with live pricing and stock in one call. - Declarative frameworks —
swm setup install <name>brings up ComfyUI / SwarmUI / vLLM / Ollama / Open WebUI / Axolotl / llm-studio idempotently; venv, custom nodes, and multi-GPU tensor parallelism handled. - Unified model store —
swm models pullauto-detects HF / Civitai / Ollama / URL refs, lands files under/workspace/models/<bucket>/, symlinks them into each framework's expected path. - Workspace persistence — three-tier S3 sync (inotify → s5cmd → tar) survives auto-down.
pod create -w <name>restores the last session. - Lifecycle guard —
auto-down/auto-stop/remindpolicies stop idle bills.
Stop condition. Don't hand off until Phase 5 passes. A pod that's "almost up" still bills.
Prerequisites
swm --versionworks (pipx install swm-gpuorbrew tap swm-gpu/swm && brew install swm).sshandscpon PATH.- At least one provider key:
swm config set runpod.api_key <key>(orvastai,lambda, …). - Optional
/workspacepersistence:swm config set b2.key_id …+swm config set storage.default b2:<bucket>.
Phase 0 — State check
swm pod list && swm use --show # running pods + active-pod selection
swm storage ls # existing workspaces in the default bucket
If a matching pod is RUNNING, set it active (swm use <name>) and skip to Phase 5. If a workspace prefix you want already exists in swm storage ls, restore it with pod create -w <name>. Otherwise continue.
Phase 1 — Clarify
Use AskQuestion:
| Question | Options |
|---|---|
| VRAM floor? | ≤16 GB / 16–24 GB / 24–48 GB / 48–80 GB / >80 GB |
| Provider? | runpod / vastai / lambda / tensordock / vultr / auto (cheapest) |
| Lifecycle? | auto-down (default) / auto-stop / remind / manual |
| Idle timeout? | 10 / 20 / 30 / 60 / 120 min |
Persist /workspace? |
yes (default) / no — one-shot, --no-storage |
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.
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.
- 4d ago First seen · 410 lines · 116 tokens per session scan A dc66b3db6de6
swm-gpu-workflow is a skill published in the GitHub repository swm-gpu/swm (24 stars, last pushed today), licensed Apache-2.0. It adds 116 tokens to every session and 5,803 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
colab-finetuning
Fine-tune LLMs on Google Colab GPUs directly from openscience. Connects to Colab runtimes via WebSocket bridge for remote training with Unsloth. Supports SFT, GRPO, DPO, vision, and TTS workflows on free T4 to Pro A100 GPUs.
debug-cuda-crash
Tutorial for debugging CUDA crashes using API logging.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
test-amplification
Methodical bug-driven test amplification for pygraphistry features. Use when hardening a feature area via user-workflow exploration, 5-Whys retrospectives, bug-taxonomy derivation, concrete test planning, implementation, and safety-gated validation.
plan
OPT-IN file-based planning for multi-session tasks. Only use when user explicitly requests it or work spans multiple sessions. For single-session work, prefer your platform's native planning features.
document-public-apis
Document undocumented public APIs in PyTorch by removing functions from coverageignorefunctions and coverageignoreclasses in docs/source/conf.py, running Sphinx coverage, and adding the appropriate autodoc directives to the correct .md or .rst doc files. Use when a user asks to remove functions from conf.py ignore…