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/sapiom/sapiom-js/sapiom-sandbox-previewnpx skills add sapiom/sapiom-js --skill sapiom-sandbox-previewgit clone --depth 1 https://github.com/sapiom/sapiom-jsWrote 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/sapiom/sapiom-js/sapiom-sandbox-preview)<a href="https://agentmods.dev/skills/sapiom/sapiom-js/sapiom-sandbox-preview"><img src="https://agentmods.dev/badge/skills/sapiom/sapiom-js/sapiom-sandbox-preview.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 | $0.00149 | $0.02011 |
| Opus 5 | $0.00075 | $0.01006 |
| Sonnet 5 | $0.00030 | $0.00402 |
| Haiku 4.5 | $0.00015 | $0.00201 |
Grade A, and why
sapiom-sandbox-preview 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sandbox Previews & App Links
Two ways to put the web app in the current project on a live URL, both driven by the
sapiom-dev MCP (npx -y @sapiom/mcp; see the Get Started guide
if it isn't connected) and both reading the same sapiom.json resource:
| You want | Tool | The URL |
|---|---|---|
| To look at it now, iterate, throw it away | sapiom_dev_sandbox_preview |
Temporary — dies with the sandbox's ttl |
| A link that lasts, or that someone else opens | sapiom_dev_app_publish |
Durable — https://apps.sapiom.ai/{org}/{slug} |
This is not agent deployment. Sapiom agents deploy with sapiom_dev_agents_deploy;
both tools here host an ordinary app (Node server, static site, API, dashboard) from your
working directory.
Prerequisite
Run sapiom_authenticate once (browser login; caches a key in ~/.sapiom/credentials.json).
sapiom_dev_sandbox_preview and sapiom_dev_app_publish return a structured
not-authenticated error otherwise; configure and check only touch local files and work
signed-out. Check with sapiom_status.
The lifecycle
sapiom_dev_sandbox_configure— creates or updates a preview resource in the project'ssapiom.json. Fill the typed arguments instead of hand-writing JSON — the config is validated and written underresources.<name>(type: "sandbox"). Returns the stored config.sapiom_dev_sandbox_check(optional) — statically validates the resources without deploying. Returns{ ok, sandboxes, issues }; fix anyissuesbefore previewing.sapiom_dev_sandbox_preview— readssapiom.json, provisions the sandbox if needed, uploads the local code, builds, starts, and exposes a public URL. Returns{ name, url, status, logs }. Passnameonly when the project defines more than one resource.sapiom_dev_app_publish— when the link needs to outlive the sandbox. See below.
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 · 148 lines · 149 tokens per session scan A 61e01d6e32c1
sapiom-sandbox-preview is a skill published in the GitHub repository sapiom/sapiom-js (19 stars, last pushed today), licensed MIT. It adds 149 tokens to every session and 2,011 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…