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 nodetool-ai/nodetool --skill sandbox-flowgit clone --depth 1 https://github.com/nodetool-ai/nodetoolWrote 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/nodetool-ai/nodetool/sandbox-flow)<a href="https://agentmods.dev/skills/nodetool-ai/nodetool/sandbox-flow"><img src="https://agentmods.dev/badge/skills/nodetool-ai/nodetool/sandbox-flow/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/nodetool-ai/nodetool/sandbox-flow"><img src="https://agentmods.dev/badge/skills/nodetool-ai/nodetool/sandbox-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.01222 |
| Opus 5.5 | $0.00012 | $0.00489 |
| Sonnet 5.5 | $0.00006 | $0.00244 |
| Haiku 4.5 | $0.00003 | $0.00122 |
Grade A, and why
sandbox-flow 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
60 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.
- package.json 10 KB
- sandbox/generated/gemini.audio.js 330 B runs code
- sandbox/generated/gemini.image.js 239 B runs code
- sandbox/generated/gemini.text.js 331 B runs code
- sandbox/generated/gemini.video.js 333 B runs code
- sandbox/generated/kie.dynamic_schema.js 215 B runs code
- sandbox/generated/lib.audio.js 1.6 KB runs code
- sandbox/generated/lib.browser.js 223 B runs code
- sandbox/generated/lib.charts.js 231 B runs code
- sandbox/generated/lib.comfy.js 802 B runs code
- sandbox/generated/lib.grid.js 232 B runs code
- sandbox/generated/lib.image.channel.js 310 B runs code
- sandbox/generated/lib.image.color_grading.js 1.2 KB runs code
- sandbox/generated/lib.image.color.js 818 B runs code
- sandbox/generated/lib.image.draw.js 1009 B runs code
- sandbox/generated/lib.image.effects.js 607 B runs code
- sandbox/generated/lib.image.enhance.js 763 B runs code
- sandbox/generated/lib.image.filter.js 1.6 KB runs code
- sandbox/generated/lib.image.js 203 B runs code
- sandbox/generated/lib.image.keyer.js 318 B runs code
- sandbox/generated/lib.image.mask.js 400 B runs code
- sandbox/generated/lib.image.warp.js 862 B runs code
- sandbox/generated/lib.pdf.js 831 B runs code
- sandbox/generated/lib.sqlite.js 237 B runs code
- sandbox/generated/lib.stable_diffusion_cpp.js 245 B runs code
- sandbox/generated/lib.svg.js 308 B runs code
- sandbox/generated/lib.video.download.js 239 B runs code
- sandbox/generated/messaging.discord.js 379 B runs code
- sandbox/generated/messaging.telegram.js 386 B runs code
- sandbox/generated/mistral.embeddings.js 227 B runs code
- sandbox/generated/mistral.text.js 336 B runs code
- sandbox/generated/mistral.vision.js 310 B runs code
- sandbox/generated/nodetool.agents.js 1.1 KB runs code
- sandbox/generated/nodetool.audio.js 2.9 KB runs code
- sandbox/generated/nodetool.audio.realtime.js 1.5 KB runs code
- sandbox/generated/nodetool.audio.synth.js 1.8 KB runs code
- sandbox/generated/nodetool.blender.js 811 B runs code
- sandbox/generated/nodetool.code.js 306 B runs code
- sandbox/generated/nodetool.compare.js 237 B runs code
- sandbox/generated/nodetool.constant.js 3.3 KB runs code
- sandbox/generated/nodetool.control.js 4.4 KB runs code
- sandbox/generated/nodetool.creative.js 786 B runs code
- sandbox/generated/nodetool.data.js 551 B runs code
- sandbox/generated/nodetool.document.js 605 B runs code
- sandbox/generated/nodetool.entity.js 562 B runs code
- sandbox/generated/nodetool.fake.js 335 B runs code
- sandbox/generated/nodetool.game.js 1.1 KB runs code
- sandbox/generated/nodetool.generators.js 974 B runs code
- sandbox/generated/nodetool.image.js 3.2 KB runs code
- sandbox/generated/nodetool.input.js 4.0 KB runs code
- sandbox/generated/nodetool.manimgx.js 454 B runs code
- sandbox/generated/nodetool.model3d.js 2.1 KB runs code
- sandbox/generated/nodetool.output.js 320 B runs code
- sandbox/generated/nodetool.script.js 787 B runs code
- sandbox/generated/nodetool.sketch.js 451 B runs code
- sandbox/generated/nodetool.storyboard.js 1.1 KB runs code
- sandbox/generated/nodetool.text.js 1.9 KB runs code
- sandbox/generated/nodetool.timeline.js 691 B runs code
- sandbox/generated/nodetool.triggers.js 1.0 KB runs code
- sandbox/generated/nodetool.variable.js 457 B runs code
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 Changed · +6 lines 633922167e99
- 1mo ago First seen · 126 lines · 31 tokens per session scan A f1f79215c4ba
sandbox-flow is a skill published in the GitHub repository nodetool-ai/nodetool (571 stars, last pushed today), licensed AGPL-3.0. It adds 31 tokens to every session and 1,222 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
pydantic-ai
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.
writing-docs
Writing CodeCompanion.nvim docs. Use when creating or editing any page in doc/.
lynkr
Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, and Codex.
pydantic-ai
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.
typecast
Use TypeCast to turn LLM output into validated, typed JVM values. Reach for it whenever code calls an LLM and then parses/validates the response by hand: extraction of case classes or Java records from text, classification/routing via sealed traits, constraint enforcement with retry, streaming partial JSON into a UI…
polymarket-trading
Use when the user wants to actually PLACE, manage, or redeem bets on Polymarket (not just read odds — that's the blockrunpredexon data tools). Covers setup (deposit wallet, funding, approvals), buy/sell with confirm gating, positions, redeeming winnings, geoblock handling, and the end-to-end flow.