Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Bangs00/claude-media-control/plugin install mediaWrote 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/bangs00/claude-media-control/config)<a href="https://agentmods.dev/skills/bangs00/claude-media-control/config"><img src="https://agentmods.dev/badge/skills/bangs00/claude-media-control/config.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00089 | $0.01593 |
| Opus 5 | $0.00044 | $0.00796 |
| Sonnet 5 | $0.00018 | $0.00319 |
| Haiku 4.5 | $0.00009 | $0.00159 |
Grade B, and why
config scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.claude/settings.json` automatically** (wrapper + backup of the previous How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requested change (may be empty): $ARGUMENTS
Current settings:
!"${CLAUDE_PLUGIN_ROOT}/scripts/media.sh" config
Pick the mode from $ARGUMENTS:
Mode A — a key was given ($ARGUMENTS is NOT empty)
The user named a specific key (e.g. display.statusline on,
statusline.marquee off). Apply it directly and report the result:
"${CLAUDE_PLUGIN_ROOT}/scripts/media.sh" config $ARGUMENTS
Valid keys:
display.progressbar— progress bar in the/media:nowreplydisplay.statusline— the statusline now-playing segmentstatusline.multiline— layout:on= each group on its own line,off= one line (unused whenstatusline.fieldshas/breaks)statusline.color— ANSI colors/bold/italic in the statusline (defaulton; theNO_COLORenv var also disables it)statusline.marquee— scroll statusline titles wider than 30 cells, one char/second (defaulton)statusline.links— which parts of the statusline segment are cmd+clickable, each switchable on its own (defaulton= all four):toggle(the ▶︎/⏸ icon toggles playback),track(title/artist jump to the playing media — the playing browser tab or Music's current track when the app is scriptable, plain app activation otherwise),app(the same jump from the app name), andseek(each progress-bar cell seeks). Takeson(all),off(none), or a comma/space list of parts —config statusline.links toggle,seekleaves the text plain and keeps the icon and bar clickable. Any part left on builds + registers the localclaude-media-control://handler app, and is refused (exit 3) when that build fails; parts switched off render exactly as they would with links off. Works in hyperlink-capable terminals (iTerm2, Ghostty, WezTerm, Kitty, VS Code)history.record— log played tracks to the local history (defaulton; view with/media:history)statusline.fields— which items the statusline shows, as an ordered comma/space list oftrack app volume progressbar time outputwith optional/line breaks (interactive:/media:statusline)style.<part>— per-item statusline styles (15 string-valued keys;config stylelists them, the valueresetrestores one,config style resetrestores all). Guided styling lives in/media:statusline.statusline reset— restore the whole statusline appearance to defaults: arrangement, explicit lines, colors, marquee, and everystyle.*key. Does not touchdisplay.statuslineor the non-statusline toggles.
Rules you must follow:
- Enabling runs a preflight. Exit code 3 means the feature cannot work right now and the
enable was refused (fail-closed by design). Explain the reason from stderr, point to
/media:doctor, and do NOT retry or work around the refusal. - Enabling
display.statuslinealso wires the segment into~/.claude/settings.jsonautomatically (wrapper + backup of the previousstatusLine; details indocs/statusline.md). Relay the wiring line the command prints — it says whether it wired, refreshed, or found a manual setup it left alone. The segment shows up on the next statusline tick, no restart needed. - A wish to unwire the statusline (remove it from settings.json, "배선
해제", "settings에서 빼줘") maps to
"${CLAUDE_PLUGIN_ROOT}/scripts/media.sh" statusline uninstall— it restores the backed-upstatusLine, removes the wrapper + backup, and turnsdisplay.statuslineoff. (Plaindisplay.statusline offonly hides the segment and keeps the wiring for a fast re-enable. Uninstalling the plugin reverts the wiring by itself.) - Disabling always succeeds.
- Afterwards show the resulting state (re-run
configwith no key if helpful).
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.
- 6d ago First seen · 104 lines · 0 tokens per session scan B 1d4aeabb7757
config is a skill published in the GitHub repository Bangs00/claude-media-control (4 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,593 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
spotify
Control Spotify on macOS. Use for playing music, controlling playback, and getting track information.
youtube-producer
Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…
video-content
Plans and scripts short-form and long-form video, and designs the packaging — titles, thumbnails, and openings — that determines whether it gets watched. Use this to script a video, plan a series, fix retention or click-through problems, design thumbnail and title concepts, or turn written content into video. For a…
visual-content
Designs and directs the visual assets that carry content — carousels, infographics, quote graphics, diagrams, and social imagery — including the generation prompts where they are AI-produced. Use this to turn a written piece into a visual format, design a carousel or infographic, create social graphics, or fix visuals…
nano-banana-prompting
This skill should be used when crafting prompts for Nano Banana Pro (Gemini image generation). Use when users want help writing image generation prompts, need guidance on prompt structure, or want to optimize their prompts for better results.
nano-banana
This skill should be used for Python scripting and Gemini image generation. Use when users ask to generate images, create AI art, edit images with AI, or run Python scripts with uv. Trigger phrases include "generate an image", "create a picture", "draw", "make an image of", "nano banana", or any image generation…