mflux: Skill for Cursor

.cursor/skills/mflux-manual-testing/SKILL.md

mflux-manual-testing is a skill for Cursor from mflux-community/mflux. It costs 25 tokens per session (993 once invoked), scanned A, original, MIT.

A checklist for manually testing changed mflux command-line tools and reviewing their generated images or other files. A command-line tool is a program operated through typed terminal commands.

In plain words
What is it for?
Use it after changing mflux CLI entry points, callbacks, metadata, image saving, flags, defaults, or models.
Why use it?
Automated tests may miss problems in real command usage, image saving, callbacks, or output quality, so the changed paths are exercised directly.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is mflux-community/mflux's own configuration. It tells Cursor how to work on mflux itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mflux configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cd ../diffusers && HF_HUB_OFFLINE=1 uv run python -c "..." # inline script; see mflux-debugging.

About the project

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.

mflux-community/mflux · 2,322 stars · on GitHub

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/mflux-community/mflux/main/.cursor/skills/mflux-manual-testing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mflux-community/mflux

Made for: Cursor.

Wrote 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.

agentmods badge for mflux-manual-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/mflux-community/mflux/mflux-manual-testing/github.svg)](https://agentmods.dev/skills/mflux-community/mflux/mflux-manual-testing)
Your own site
<a href="https://agentmods.dev/skills/mflux-community/mflux/mflux-manual-testing"><img src="https://agentmods.dev/badge/skills/mflux-community/mflux/mflux-manual-testing/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.

agentmods 80×15 button for mflux-manual-testing

Your own site · 80×15
<a href="https://agentmods.dev/skills/mflux-community/mflux/mflux-manual-testing"><img src="https://agentmods.dev/badge/skills/mflux-community/mflux/mflux-manual-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 993 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.00993
Opus 5 $0.00013 $0.00496
Sonnet 5 $0.00005 $0.00199
Haiku 4.5 $0.00003 $0.00099

Measured 11d ago against content hash 8e582d96207a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mflux-manual-testing 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 11d 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.

.cursor/skills/mflux-manual-testing/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mflux manual testing

Some regressions (especially in CLIs and image IO) are easiest to catch by running the commands and visually inspecting outputs. This skill provides a lightweight, change-driven manual test checklist.

When to Use

  • You changed any CLI entrypoint(s) under src/mflux/models/**/cli/.
  • You touched callbacks (e.g. stepwise output, memory saver) or metadata/image saving.
  • Tests are green but you want confidence in real command usage.

Strategy (change-driven)

  • Identify what changed on your branch (new flags, default behavior changes, new callbacks, new models).
  • Only run manual checks for the touched areas; don’t try to exercise every CLI.
  • Prefer 1–2 seeds and a small step count (e.g. 4) for fast iteration, unless the change affects convergence/quality.
  • Before manual CLI testing, reinstall the local tool executables so you’re testing the latest code:
uv tool install --force --editable --reinstall .

Core CLI checks (pick what’s relevant)

  • Basic generation: run the CLI once with a representative prompt and confirm the output is not “all noise”.
  • Model saving (if relevant): if you touched weight loading/saving or model definitions, run mflux-save for the affected model(s) and verify:
    • the output directory is created
    • the command completes without missing-file errors
  • Run from disk (if relevant): if you touched save/load paths or model resolution, generate from a locally saved model directory by passing --model /full/path/to/saved-model and confirm it runs and produces a sane image.
  • Stepwise outputs (if relevant): run with --stepwise-image-output-dir and confirm:
    • step images are written for each step
    • the final step image matches the final output image qualitatively
    • the composite image is created
  • Low-RAM path (if relevant): run with --low-ram and confirm:
    • generation completes
    • output quality is sane (no unexpected all-noise output)
  • Metadata (if relevant): run with --metadata and confirm the .metadata.json sidecar is emitted and looks consistent.

Read the full file on GitHub · 81 lines

Changes

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.

  1. 11d ago First seen · 81 lines · 25 tokens per session scan A 8e582d96207a

Subscribe to this mod's changes

mflux-manual-testing is a skill published in the GitHub repository mflux-community/mflux (2,322 stars, last pushed 8d ago), licensed MIT. It adds 25 tokens to every session and 993 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

chrome-cdp

Drive a headless Chrome over the Chrome DevTools Protocol (CDP) for browser QA — navigate, click, fill forms, read the DOM/accessibility tree, screenshot, and assert. Use whenever a task requires loading a web page and interacting with it like a user. Chrome is launched by a bash step (recipe below); this skill…

mattzcarey/shippie · 91 tokens

quality-flywheel

Evaluate and improve GenAI models and agents using the Google GenAI Evaluation SDK. Creates eval datasets (from session traces or synthetic generation), selects and configures metrics (RubricMetric, LLMMetric, CodeExecutionMetric), executes evals via client.evals.evaluate(), and analyzes results to suggest concrete…

GoogleCloudPlatform/vertex-ai-samples · 128 tokens

submit-github-bug-issue

Use when converting QA findings, black-box failures, red-team reports, regression evidence, or local bug notes into GitHub Issues for NVIDIA/TensorRT-Model-Connect. Standardizes checking issue templates, checking labels, de-duplicating existing issues, drafting a bug report, creating the issue on GitHub, applying the…

NVIDIA/TensorRT-Model-Connect · 82 tokens

transform-model

Add a Hugging Face or local checkpoint to TensorRT-Model-Connect as a self-contained family, or extend the family that already owns it.

NVIDIA/TensorRT-Model-Connect · 33 tokens

AI/ML Model Testing

Testing machine learning models including accuracy validation, bias detection, drift monitoring, A/B testing, and model regression testing.

PramodDutta/qaskills · 29 tokens

setup-trtmc-environment

Prepare a TensorRT-Model-Connect development or validation environment from a fresh checkout on a host without a known working setup.

NVIDIA/TensorRT-Model-Connect · 32 tokens