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/setting-up-dev-envnpx skills add fusedio/fused-render --skill setting-up-dev-envgit 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 | $0.00055 | $0.00826 |
| Opus 5 | $0.00028 | $0.00413 |
| Sonnet 5 | $0.00011 | $0.00165 |
| Haiku 4.5 | $0.00006 | $0.00083 |
Grade A, and why
setting-up-dev-env 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setting Up the Dev Env
Overview
Every fresh checkout/worktree needs a 3.12 venv and a built React shell — both are gitignored, so they don't carry into a worktree. Without them, pytest/python silently run against the wrong interpreter or fail on missing deps, and every server test dies with RuntimeError: React shell not built.
Running the Dev Server
Use scripts/dev.sh — never launch python -m fused_render.cli (or uvicorn) directly. It does almost all the setup for you: bootstraps a repo-local .venv (with [fused,bundled]) if missing, npm installs the frontend, builds shell-dist/, then runs vite build --watch + the server with Python auto-reload and per-worktree port/state isolation.
scripts/dev.sh # defaults
scripts/dev.sh --port 9000 # extra args pass through to the server
Setup for Tests
dev.sh covers the server, but its auto-venv has [fused,bundled] only — not the dev extra (pytest/xdist). And tests need a built shell-dist/ or create_app() refuses to start. So the venv install is the one manual step:
uv venv --python 3.12 .venv # pinned: matches what dev.sh and all three installers use
uv pip install --python .venv/bin/python -e ".[dev,bundled,fused]" # dev extra now includes pytest-xdist
For shell-dist/: if you've run scripts/dev.sh, it's already built. If you'll only run tests and never start the server, build it once directly (repo uses npm, per package-lock.json):
cd frontend && npm install && npm run build && cd ..
Verify: ls fused_render/static/shell-dist/index.html and .venv/bin/python -m pytest -q (~1170 pass).
Reference
| Item | Why |
|---|---|
| Python 3.12 | pinned, not a default (D214): the server passes its own interpreter to uv sync as the base for every project venv, so this version decides which wheels those venvs can resolve. A 3.14 venv made project venvs cp314, and a folder declaring tensorflow (no cp314 wheels) was an unresolvable dead end. 3.12 is what all three installers already ship, so a dev checkout matches the shipped app. scripts/dev.sh enforces it and rebuilds a .venv that is on anything else |
dev extra |
pytest + httpx (backs TestClient) |
bundled extra |
duckdb, pandas, numpy, pyarrow, pillow… (templates + daemons). NOT the geo/PDF/plotting stack any more (D276) — map, vector, pdf_studio and friends declare those in their own folder pyproject.toml, and the server installs them into a project venv on first render |
fused extra |
compute-engine wheel for /api/run |
| frontend build | create_app() refuses to start without shell-dist/ |
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 · 49 lines · 55 tokens per session scan A 36f1aa5502c6
setting-up-dev-env is a skill published in the GitHub repository fusedio/fused-render (11 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 826 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…