MFLUX is a native MLX implementation of generative image models that runs locally on Mac computers. It is for generating images with supported models through command-line tools or a Python API. The catalogue skills and instruction support workflows built around these image-generation models.
Borrowing it
Nothing to install: this file belongs to mflux-community/mflux. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mflux-community/mflux/main/.cursor/skills/mflux-dev-env/SKILL.mdgit clone --depth 1 https://github.com/mflux-community/mfluxWrote 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/mflux-community/mflux/mflux-dev-env)<a href="https://agentmods.dev/skills/mflux-community/mflux/mflux-dev-env"><img src="https://agentmods.dev/badge/skills/mflux-community/mflux/mflux-dev-env/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/mflux-community/mflux/mflux-dev-env"><img src="https://agentmods.dev/badge/skills/mflux-community/mflux/mflux-dev-env.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 | $0.00411 |
| Opus 5 | $0.00015 | $0.00205 |
| Sonnet 5 | $0.00006 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
mflux-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 9d 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.
What it actually says
mflux dev environment
This repo expects macOS arm64 and prefers uv + justfile recipes.
When to Use
- You’re setting up the repo locally or diagnosing environment/setup issues.
- You need the canonical way to run lint/format/check/build/test.
Instructions
- Prereq:
just≥ 1.50 (brew install just). CI lints the justfile withjust --fmt --check; runjust fmt-justfileto auto-fix formatting. - Prefer justfile recipes:
- Install:
just install - Lint:
just lint - Format:
just format - Pre-commit suite:
just check - Build:
just build
- Install:
- Prefer
uv run ...for running Python commands to ensure the correct environment. - When running tests, keep
MFLUX_PRESERVE_TEST_OUTPUT=1enabled (the justfile test recipes already do this).
Type checking (ty)
- The type checker is astral's
ty, pinned exactly inpyproject.tomldev deps (mirrored in.pre-commit-config.yamland run in CI). Run it withjust typecheck(oruv run ty check). [tool.ty.rules]inpyproject.tomlcarries a one-time migration baseline (mypy → ty): every rule listed there had pre-existing violations and is set to"ignore", with violation counts in comments.- Planned burn-down: we intend to re-enable these rules piecemeal — delete one ignore line, fix all resulting
ty checkerrors, commit, repeat. Prefer starting with low-count rules. Do not add new ignore lines; new code must pass all rules not in the baseline.
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.
- 9d ago First seen · 32 lines · 31 tokens per session scan A ae24a0b30f6b
mflux-dev-env is a skill published in the GitHub repository mflux-community/mflux (2,315 stars, last pushed 5d ago), licensed MIT. It adds 31 tokens to every session and 411 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
dataset-discovery
Multi-source ML dataset discovery.
diffusers-ascend-pipeline
A guide for running image and video generation pipelines on Huawei Ascend NPUs with the Diffusers library. Diffusers is a software library for using generative models, and the guide covers model pipelines, memory settings, LoRA adapters, and multi-card inference.
diffusers-ascend-weight-prep
A model-weight preparation tool for Diffusers, a library for running image and other generative models, on Huawei Ascend NPU hardware. It downloads weights from Hugging Face or ModelScope and can create placeholder weights from configuration files for business testing.
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.