Runpod

What it does

When your agent uses it

• Setting up RunPod endpoints
• Deploying Docker images
• Managing GPU resources
• Troubleshooting endpoint issues

Example prompts

• “/runpod”

Requirements

• Docker
• A credential in RUNPOD_API_KEY
• A credential in R2_SECRET_ACCESS_KEY

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1Creates a RunPod template from the Docker image
2. 2Creates a serverless endpoint with appropriate GPU
3. 3Saves the endpoint ID to .env (e.g. RUNPOD_QWEN_EDIT_ENDPOINT_ID)

What it can do on your machine

Read from SKILL.md and the folder at commit 2c99460. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • uv
  • docker
  • aws

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • api.runpod.io
  • api.runpod.ai
  • runpod.io

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • R2_ACCESS_KEY_ID
  • R2_SECRET_ACCESS_KEY
  • RUNPOD_API_KEY
  • AWS_ACCESS_KEY_ID
  • AWS_SECRET_ACCESS_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Runpod loads about 2.1k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 734 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~70

When it runs · the whole SKILL.md, loaded when a task matches

~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:14

  # 2. Add API key to .env

• NoteMentions a .env fileSKILL.md:15

  echo "RUNPOD_API_KEY=your_key_here" >> .env

• NoteMentions a .env fileSKILL.md:28

  3. Saves the endpoint ID to `.env` (e.g. `RUNPOD_QWEN_EDIT_ENDPOINT_ID`)

• NoteMentions a .env fileSKILL.md:70

  Each tool stores its endpoint ID in `.env`:

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from digitalsamba/claude-code-video-toolkit at commit 2c99460, republished under its MIT licence (© digitalsamba). 734 words, ~2,085 tokens.

name

runpod

description

Cloud GPU processing via RunPod serverless. Use when setting up RunPod endpoints, deploying Docker images, managing GPU resources, troubleshooting endpoint issues, or understanding costs. Covers all 5 toolkit images (qwen-edit, realesrgan, propainter, sadtalker, qwen3-tts).

# 1. Create account at https://runpod.io
# 2. Add API key to .env
echo "RUNPOD_API_KEY=your_key_here" >> .env

# 3. Deploy any tool with --setup
uv run tools/image_edit.py --setup
uv run tools/upscale.py --setup
uv run tools/dewatermark.py --setup
uv run tools/sadtalker.py --setup
uv run tools/qwen3_tts.py --setup

Local CLI → Upload input to cloud storage → RunPod API → Poll for result → Download output

workersMin: 0    — Scale to zero when idle (no cost)
workersMax: 1    — Max concurrent jobs (increase for throughput)
idleTimeout: 5   — Seconds before worker scales down

query { myself { endpoints { id name gpuIds templateId workersMax workersMin } } }

query { myself { currentSpendPerHr spendDetails { localStoragePerHour networkStoragePerHour gpuComputePerHour } } }

query { myself { pods { id name runtime { uptimeInSeconds } machine { gpuDisplayName } desiredStatus } } }

mutation { saveEndpoint(input: {
  id: "endpoint_id",
  name: "endpoint-name",
  templateId: "template_id",
  gpuIds: "AMPERE_24",
  workersMin: 0,
  workersMax: 1
}) { id gpuIds } }

{
  "jobs": { "completed": 16, "failed": 1, "inProgress": 0, "inQueue": 2, "retried": 0 },
  "workers": { "idle": 0, "initializing": 1, "ready": 0, "running": 0, "throttled": 0 }
}

gpuIds: "AMPERE_24,ADA_24"   # Try 3090 first, fall back to 4090

AWS_ACCESS_KEY_ID="$R2_ACCESS_KEY_ID" \
AWS_SECRET_ACCESS_KEY="$R2_SECRET_ACCESS_KEY" \
aws s3api list-objects-v2 \
  --bucket "$R2_BUCKET_NAME" \
  --endpoint-url "https://${R2_ACCOUNT_ID}.r2.cloudflarestorage.com" \
  --region auto

docker buildx build --platform linux/amd64 -t ghcr.io/conalmullan/video-toolkit-<name>:latest docker/runpod-<name>/
docker push ghcr.io/conalmullan/video-toolkit-<name>:latest

© digitalsamba, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/runpod of digitalsamba/claude-code-video-toolkit.

Open the folder on GitHubat commit 2c99460