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 skills add runpod/runpod-plugins-official --skill runpod-flashgit clone --depth 1 https://github.com/runpod/runpod-plugins-officialWrote 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/runpod/runpod-plugins-official/runpod-flash)<a href="https://agentmods.dev/skills/runpod/runpod-plugins-official/runpod-flash"><img src="https://agentmods.dev/badge/skills/runpod/runpod-plugins-official/runpod-flash/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/runpod/runpod-plugins-official/runpod-flash"><img src="https://agentmods.dev/badge/skills/runpod/runpod-plugins-official/runpod-flash.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00115 | $0.03714 |
| Opus 5.5 | $0.00046 | $0.01486 |
| Sonnet 5.5 | $0.00023 | $0.00743 |
| Haiku 4.5 | $0.00012 | $0.00371 |
Grade A, and why
runpod-flash 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runpod SDK apps (Flash)
For an explicit Dockerfile/template project request, use runpod-build-template. Do not replace that deliverable with Flash unless the user chooses its code-first workflow.
Write Python locally, run it on remote Runpod GPUs/CPUs with rp flash dev, then
rp flash deploy to ship. Flash is part of the runpod package (2.0): one SDK, one
rp CLI, one login. The standalone runpod-flash package is deprecated and gets no fixes
after October 29, 2026.
rp --help and rp flash <command> --help are authoritative for the command surface.
This skill is the mental model, the decision rules, and the gotchas that help output does not
carry. Confirm the installed version with pip show runpod before concluding a command or
parameter is unavailable.
Which SDK is this project on?
Check before writing code. The two APIs do not mix.
| You see | Project is on | Do |
|---|---|---|
import runpod, runpod.App(...), @app.queue, rp flash ... |
Runpod SDK 2.0 | This file + reference/ |
from runpod_flash import Endpoint, @Endpoint(...), flash dev, runpod-flash in deps |
Legacy runpod-flash | reference/runpod-flash-legacy.md to maintain it, reference/migrate-from-runpod-flash.md to move it |
| A new project | Runpod SDK 2.0 | Start below |
Write new code on the SDK. For an existing runpod-flash project, propose migrating and
check its Known differences first; don't migrate silently.
If the SDK path fails on an SDK bug, runpod-flash is the fallback: a traceback inside
runpod/apps/, a worker that crashes before your function runs, or the same code working on
runpod-flash. Upgrade runpod first; the steps to check for a fix and fall back are in
reference/runpod-flash-legacy.md.
Worked examples first for anything multi-step. Flash appears in end-to-end paths:
03 variant B (whisper endpoint),
07 (network-volume handoff) and
08 (fine-tune → serve); the full index is
runpod/golden-paths/README.md. Runnable single-file apps
live in examples/.
What ships with it
21 files 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.
- evals/client-external-image.eval.md 1.1 KB
- evals/connect-existing-endpoint.eval.md 942 B
- evals/cpu-gpu-pipeline.eval.md 1.2 KB
- evals/dev-loop-iteration.eval.md 2.7 KB
- evals/fixtures/dev-loop/main.py 613 B runs code
- evals/lb-multi-route-api.eval.md 1.1 KB
- evals/migrate-runpod-flash-project.eval.md 1.9 KB
- evals/qb-gpu-function.eval.md 1.0 KB
- evals/sdk-failure-fallback.eval.md 1.5 KB
- evals/volume-cache-model-load.eval.md 2.1 KB
- examples/api_model_service.py 1.2 KB runs code
- examples/call_deployed.py 912 B runs code
- examples/cpu_gpu_pipeline.py 1.1 KB runs code
- examples/queue_gpu.py 881 B runs code
- examples/README.md 1.7 KB
- examples/train_then_serve.py 1.3 KB runs code
- reference/api.md 9.3 KB
- reference/migrate-from-runpod-flash.md 7.8 KB
- reference/patterns.md 8.6 KB
- reference/runpod-flash-legacy.md 6.0 KB
- reference/setup-and-cli.md 4.8 KB
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 · 223 lines · 115 tokens per session scan A 82cb5df16082
runpod-flash is a skill published in the GitHub repository runpod/runpod-plugins-official (48 stars, last pushed yesterday), licensed Apache-2.0. It adds 115 tokens to every session and 3,714 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-11-06.
runpod-flash compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| runpod-flashrunpod/runpod-plugins-official | Skill | 48 | yesterday | Apache-2.0 | A | 115 | Claude Code |
| modalericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 78 | Claude Code, Codex |
| temporal-python-testingwshobson/agents | Skill | 42k | yesterday | MIT | A | 45 | Claude Code |
| hf-cloud-python-env-setuphuggingface/skills | Skill | 11k | 7d ago | Apache-2.0 | A | 128 | Claude Code |
| aws-sdk-python-usageaws/agent-toolkit-for-aws | Skill | 3.4k | yesterday | Apache-2.0 | A | 120 | Claude Code |
| dstack-prototypingdstackai/dstack | Skill | 2.3k | yesterday | MPL-2.0 | A | 80 | Claude Code, Codex |
| manimgl-best-practicescalesthio/OpenMontage | Skill | 77k | 3d ago | AGPL-3.0 | A | 167 | Claude Code, Codex |