mflux

Use when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and misreading has a real cost, or when text reads as dense, hedged, or easy to misparse. Triggers: disambiguate, STE100 rewrite, apply Simplified Technical English, plain-language rewrite, controlled-language rewrite, rewrite so an agent cannot misread this. Not for creative or marketing copy.

Navigate MFLUX CLI capabilities, locate commands by area, and summarize supported features.

Debug MLX ports by comparing against a PyTorch/diffusers reference via exported tensors/images (export-then-compare).

Set up and work in the mflux dev environment (arm64 expectation, uv, justfile recipes, lint/format/test).

Manually validate mflux CLIs by exercising the changed paths and reviewing output images/artifacts.

Port ML models into mflux/MLX with correctness-first validation, then refactor toward mflux style.

Write a hermetic "tiny" model-saving test for an mflux model — a fast twin of the slow save/load test that runs the real ModelSaver/WeightLoader/WeightApplier seam on real component classes at toy dimensions, with no downloads or image generation. Use when asked to "make tiny test for <model>".

Make a clean PR in mflux (inspect diff, quick verification, commit, push, open PR) using repo conventions.

Write the PR body for the current mflux branch and show it to the developer for approval. Fills the What section, the release-note block and the Verification section of the PR template. Use when the developer asks to write, fill or update a PR description or a release note.

Prepare a release in mflux (version bump + uv lock; release notes are harvested from PR release-note blocks and live in GitHub Releases). Use when preparing a release branch or release PR.

Run tests in mflux (fast/slow/full), preserve image outputs, and handle golden image diffs safely.

Remediates GitHub Dependabot alerts for mflux in one dependency-security change. Use when auditing, clamping, or upgrading Python dependencies in pyproject.toml and uv.lock, or when validating whether a branch will close Dependabot findings before opening a PR.