mlflow: Skill for Claude Code

.claude/skills/upload-media/SKILL.md

upload-media is a skill for Claude Code from mlflow/mlflow. It costs 49 tokens per session (199 once invoked), scanned A, original, Apache-2.0.

A command-line workflow for uploading local images or videos to GitHub and receiving URLs for them. The URLs can then be embedded in pull requests, issues, or comments.

In plain words
What is it for?
Uploading screenshots, screen recordings, and other local media for use in GitHub pull-request bodies, issues, or comments.
Why use it?
It removes the manual step of finding an attachment URL before adding media to GitHub discussion. It also documents the formatting needed for images and videos to display correctly.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is mlflow/mlflow's own configuration. It tells Claude Code how to work on mlflow 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 mlflow configures →

About the project

MLflow is an open-source platform for building, testing, monitoring, and managing applications that use machine-learning models, large language models, or AI agents. Teams use it to inspect application behavior, evaluate results, manage prompts, and control access to models and data in production. Catalogue add-ons provide coding-agent workflows for MLflow.

mlflow/mlflow · 27,822 stars · on GitHub · mlflow.org

Reuse

Borrowing it

Nothing to install: this file belongs to mlflow/mlflow. 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/mlflow/mlflow/master/.claude/skills/upload-media/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mlflow/mlflow

Made for: Claude Code.

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 upload-media

README.md
[![agentmods](https://agentmods.dev/badge/skills/mlflow/mlflow/upload-media.svg)](https://agentmods.dev/skills/mlflow/mlflow/upload-media)
Your own site
<a href="https://agentmods.dev/skills/mlflow/mlflow/upload-media"><img src="https://agentmods.dev/badge/skills/mlflow/mlflow/upload-media.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 199 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00049 $0.00199
Opus 5 $0.00024 $0.00100
Sonnet 5 $0.00010 $0.00040
Haiku 4.5 $0.00005 $0.00020

Measured 6d ago against content hash 7ba9eb8537c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

upload-media 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 6d 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.

.claude/skills/upload-media/SKILL.md · 18 lines

What it actually says

Upload media

Files: $ARGUMENTS (when empty, the paths named in the request).

uv run --package skills skills upload-media <path>...  # prints "<path>\t<url>" per file

Embed an image as ![alt](url). Embed a video as the bare URL in its own paragraph, blank line above and below; anything else renders as a link rather than a player.

No GitHub documentation covers this endpoint, so it can stop working without notice. Source: https://x.com/steipete/status/2088486859244741020.

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. 6d ago First seen · 18 lines · 49 tokens per session scan A 7ba9eb8537c5

Subscribe to this mod's changes

upload-media is a skill published in the GitHub repository mlflow/mlflow (27,822 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 199 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.

Related

Other skills, from other repositories

molecule-visualization

Publication-quality molecular visualization. 2D structure drawings (PNG/SVG), molecule grids with property annotations, scaffold highlighting, protein-ligand interaction diagrams, and interactive 3D views.

synthetic-sciences/openscience · 44 tokens

flux2-lora-training

Comprehensive reference for training LoRAs on FLUX.2 Klein 9B and Qwen Image Edit 2511 models. Use this skill whenever the user asks about: training LoRAs for flux2/flux 2 klein/qwen-image-edit, before/after edit LoRAs (head swap, face swap, image editing), inpainting LoRAs, training at larger resolutions, latent…

AnastasiyaW/codex-claude-code-config · 242 tokens

pixel-art-storyboard

Convert short scene descriptions, book/album cover briefs, or 2-paragraph synopses into seamless-loop animated pixel-art covers rendered as self-contained HTML+canvas. Companion skill to pixel-art-studio. Use when the user asks to "make a cover for", "animated book cover", "looped pixel scene", "convert this story…

AnastasiyaW/codex-claude-code-config · 303 tokens

product-meaning-extractor

Deep product analysis before creating videos, presentations, or ads. Use when: 'analyze product', 'extract value', 'product brief', 'what makes this product special', 'prepare brief', 'understand the product', 'video brief'. Takes a URL or product description and outputs a structured brief with core insight, enemy…

AnastasiyaW/codex-claude-code-config · 155 tokens

video-narrative-arc

Proven narrative arc templates for product videos and ads. Use when: 'write script', 'video structure', 'narrative arc', 'scene plan', 'storyboard', '15 second video', '30 second video', '60 second video', 'how to structure the video', 'video script template'. Provides beat-by-beat templates with timing, emotional arc…

AnastasiyaW/codex-claude-code-config · 167 tokens

remotion-production-guide

Remotion (React video framework) production guide with Apple-style design rules. Use when: 'create video with remotion', 'remotion project', 'render video', 'product demo video', 'animated video', 'video from code'. Covers project setup, animation library, spring presets, typography rules, color palettes, pacing…

AnastasiyaW/codex-claude-code-config · 150 tokens