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/fusedio/fused-render/fused-render-usagenpx skills add fusedio/fused-render --skill fused-render-usagegit clone --depth 1 https://github.com/fusedio/fused-renderWhat 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 | $0.00051 | $0.01070 |
| Opus 5 | $0.00026 | $0.00535 |
| Sonnet 5 | $0.00010 | $0.00214 |
| Haiku 4.5 | $0.00005 | $0.00107 |
Grade A, and why
fused-render-usage 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 3d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using a fused-render project
fused-render is a local file-explorer desktop app that runs entirely on 127.0.0.1 — no accounts, no cloud. It browses any directory in the browser, previews files, and live-renders .html views that call local Python. This skill covers running and using the app; it does not cover writing views (that's fused-render-authoring).
This skill assumes the FusedRender desktop app is already running — there's a single instance per user, serving on 127.0.0.1. Everything below is a way to open something into that running instance.
Opening a file, view, or directory
Hand the path to the app — it opens as a full-shell view (/explorer/view/<path>) in a browser tab, reusing the running instance:
| Platform | Open a path |
|---|---|
| macOS | open -a FusedRender <path> |
| Linux | gtk-launch fused-render <path>, right-click → Open With → FusedRender, or the AppImage binary FusedRender-<ver>.AppImage <path> |
| Windows | FusedRender.exe <path>, or right-click → Open with → FusedRender |
Opening a directory lands the explorer there; opening a file previews it; opening an .html view renders it.
Opening by URL (view / embed / preview templates)
Everything the app shows is a URL, so any view is bookmarkable and shareable. The running app already has a tab open — reuse its http://127.0.0.1:<port> from the address bar and swap the path.
The filesystem path rides in the URL after a mode prefix, with its leading slash dropped and each segment URL-encoded (space → %20). /Users/me/proj/dash.html → …/explorer/view/Users/me/proj/dash.html.
| Path | Renders |
|---|---|
/ |
Redirects to /apps (the app hub). /explorer is the file-explorer homepage — click to browse. |
/explorer/view/<path> |
Full-shell mode — the page wrapped in explorer chrome (sidebar, breadcrumb, preview header). What the app opens when you hand it a path. |
/explorer/embed/<path> |
Embed mode — the page chrome-free (no sidebar/breadcrumb/header). Best for opening a specific view on its own or for a screenshot. |
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.
- 3d ago First seen · 58 lines · 51 tokens per session scan A 06f2a21951d3
fused-render-usage is a skill published in the GitHub repository fusedio/fused-render (11 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 1,070 once invoked, about $0.0003 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…