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-background-appsnpx skills add fusedio/fused-render --skill fused-render-background-appsgit clone --depth 1 https://github.com/fusedio/fused-renderWrote 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/fusedio/fused-render/fused-render-background-apps)<a href="https://agentmods.dev/skills/fusedio/fused-render/fused-render-background-apps"><img src="https://agentmods.dev/badge/skills/fusedio/fused-render/fused-render-background-apps.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 | $0.00047 | $0.01374 |
| Opus 5 | $0.00023 | $0.00687 |
| Sonnet 5 | $0.00009 | $0.00275 |
| Haiku 4.5 | $0.00005 | $0.00137 |
Grade A, and why
fused-render-background-apps 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 today.
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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Background apps
Three ways folder's Python runs:
| Path | Lifetime | State survives? | Idle-reaped? |
|---|---|---|---|
/api/run (fused.runPython) |
fresh subprocess, 60 s kill | no | n/a |
main = "x.py" |
shipped warm worker, plain main(**params) |
yes | after idle_timeout_s (default 900 s) |
daemon = "x.py" |
own HTTP daemon | yes | no by default; set idle_timeout_s > 0 to opt in |
Pick daemon = only when idle-reap is the actual problem (websocket/poll server, held device/socket, tray UI). State between calls minutes apart = main =, no daemon script.
Manifest
Folder's pyproject.toml: [tool.fused-render.app] with EXACTLY ONE of daemon = / main = (path inside folder, file not dir). Optional idle_timeout_s (0 = resident). Bad manifest silently rejected (read as "no manifest") — rules in background_apps.load_manifest; check GET /api/apps/background/status?html=<page> if unsure yours parsed.
Daemon contract
Plain script run as [interpreter, daemon.py, --status <path>, --cache <dir>, --version <str>]. Read tests/fixtures/background_app/daemon.py (minimal stdlib reference) before writing one. Race-free sequence: parse args → bind 127.0.0.1:0 → atomically publish {port, token, pid} to status file (temp + os.replace, BEFORE serve_forever) → serve. Require random token on every request (parent proxies via /api/engines/<id>/proxy/, but any local process can hit port). GET /ping → {"ok": true, "version": <the --version you were GIVEN — never hardcode, defeats staleness respawn>}. GET /quit → shutdown() on separate thread (same-thread deadlocks ThreadingHTTPServer).
Guest-process rules: may die anytime (persist under --cache with temp+os.replace); respawns start empty — reinit() replay does NOT apply here; tolerate mid-request death.
Environment (differs from /api/run)
- Runs folder's OWN declared env, no ancestor walk, no bundled union —
[project]list complete. No project deps →sys.executable;import fused_rendernever available. templates/sharedNOT on sys.path →import fused_ai/import background_appfail. Bootstrap: read<FUSED_RENDER_HOME_DIR or ~/.fused-render>/server.json,sys.path.insert(0, info["shared"]).background_appmodule (from shared):status(),stop(),restart(),set_autostart(bool)— daemon's own control channel. NeedsFUSED_RENDER_APP_DIRenv (set for managed daemons); raisesNotUnderEngine,ServerNotRunning,BackgroundAppError— catch them.- Server-startup autostart skips folders whose venv isn't built (open page once first);
start()falls back tosys.executable.
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.
- today Changed · -238 lines · -36 tokens per session dc3392dcac46
- 4d ago First seen · 300 lines · 83 tokens per session scan A 2e11d4b2ae85
fused-render-background-apps is a skill published in the GitHub repository fusedio/fused-render (11 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 1,374 once invoked, about $0.0002 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…