A command-line tool that adds Apple device frames to screenshots and screen recordings. It can detect the device from image dimensions and process folders of files.

Use it to create device mockups, check which device frame matches an image, and batch-frame screenshots or videos. Video processing requires ffmpeg and ffprobe.

It removes the need to add device bezels by hand or manage separate image and video editing workflows.

frames-cli — Skill by viticci

Install

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.

agentmods

npx agentmods add skills/viticci/frames-cli/skill

Any agent

npx skills add viticci/frames-cli --skill skill

Clone the repo

git clone --depth 1 https://github.com/viticci/frames-cli

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,030 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.

Model	Per session	Once invoked
Fable 5	$0.00055	$0.04030
Opus 5	$0.00028	$0.02015
Sonnet 5	$0.00011	$0.00806
Haiku 4.5	$0.00006	$0.00403

Measured 2d ago against content hash 60bb35a58cf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frames-cli 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 2d 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.

skill/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apple Frames CLI

frames 1.3.2 is a single-file Python CLI that applies Apple device bezels to screenshots and videos, auto-detects devices from input dimensions, applies masks when needed, and can merge multiple framed results. Video support uses external ffmpeg 5.1+ and ffprobe 5.1+ with no extra Python media stack.

What Agents Should Know

frames is the default command. frames screenshot.png and frames frame screenshot.png are equivalent.
Use frames --json ... for automation. Put global flags such as --json, --assets, and --verbose before subcommands for the broadest compatibility.
Device support comes from the installed asset bundle, not hardcoded names in this skill. Use frames list and frames list-colors as the source of truth when exact names matter.
On macOS, the default asset location is the Apple Frames shortcut folder in iCloud Drive. That avoids downloading a second copy when the user already has the shortcut assets installed.
Use frames video ... for .mp4, .mov, and .m4v; the default frames ... path is for images.
Use frames video-info ... to probe videos and resolve the matching frame metadata without rendering.
Video framing requires external ffmpeg 5.1+ and ffprobe 5.1+. frames setup checks this and can offer a Homebrew install on macOS; frames doctor reports video tool readiness.
frames video preserves single-video audio by default. Pass --strip-audio when the user asks for silent output, privacy-safe delivery, or validation clips where audio does not matter.
frames video --preset compact|balanced|best controls MP4 export size/quality; best is the default. Video exports report output file size and source-vs-output savings in human and JSON output.
Use frames video --alpha ... or frames video --background transparent ... for transparent ProRes 4444 .mov output. This works for single videos and merged videos; MP4/H.264 and MP4/HEVC do not support alpha.
Explicit transparent output file paths must use a .mov extension. Use an output directory when you want the CLI to pick the .mov filename.
Use frames video --rotate clockwise|counterclockwise|180 ... when a screen recording's visual orientation differs from its encoded dimensions. This is common with some landscape iPad recordings that probe as portrait.
Non-alpha MP4 exports pad odd-sized Apple frame assets to even encoded dimensions instead of letting ffmpeg crop silently. Check output_dimensions and padded in JSON output.

Read the full file on GitHub · 237 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.

2d ago First seen · 237 lines · 55 tokens per session scan A 60bb35a58cf0

Subscribe to this mod's changes

frames-cli is a skill published in the GitHub repository viticci/frames-cli (263 stars, last pushed 19d ago), licensed MIT. It adds 55 tokens to every session and 4,030 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.

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens