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.
npx agentmods add skills/jaychempan/coding-with-beat/cwbnpx skills add jaychempan/coding-with-beat --skill cwbgit clone --depth 1 https://github.com/jaychempan/coding-with-beatWrote 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/jaychempan/coding-with-beat/cwb)<a href="https://agentmods.dev/skills/jaychempan/coding-with-beat/cwb"><img src="https://agentmods.dev/badge/skills/jaychempan/coding-with-beat/cwb.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 | $0.00056 | $0.02641 |
| Opus 5 | $0.00028 | $0.01321 |
| Sonnet 5 | $0.00011 | $0.00528 |
| Haiku 4.5 | $0.00006 | $0.00264 |
Grade C, and why
cwb scanned grade C with 2 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 4d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -LsSf https://raw.githubusercontent.com/jaychempan/coding-with-beat/main/bootstrap_codex.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Do **not** run a shell `curl` preflight against `/mcp`. Streamable HTTP MCP How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
coding-with-beat — Music Control
You have a coding-with-beat MCP server running locally. Use its tools to control music without leaving the coding session.
When to activate
- User says: "play", "pause", "skip", "next", "what's playing", "volume", "lyrics"
- User names a song, artist, or genre: "play some lofi", "put on 周杰伦"
- User types
cwb <command>or/cwb <command> - User asks about DJ Buddy or music status
Available MCP tools
Call these tools directly — do not shell out to cwb unless MCP is unavailable.
| Tool | Purpose |
|---|---|
play |
Resume playback |
resume |
Resume (alias for play) |
toggle |
Toggle play / pause |
play_song(query) |
Search and play by name/artist/genre |
play_number(number) |
Play track #n from last search or list |
play_playlist(name) |
Play a named playlist |
smart_search(queries) |
Mood/vibe/scene search — pass 2–3 angle queries |
pause |
Pause |
next_track |
Skip to next |
prev_track |
Go to previous |
now_playing |
Get current track info |
set_volume(percent) |
Volume 0–100 |
seek(seconds) |
Seek to position (seconds or mm:ss) |
set_play_mode(mode) |
shuffle | sequential | repeat | repeat_one |
like_current |
Like / favourite current track |
search(query) |
Search library + Apple Music catalog |
list_library(limit) |
List all library tracks |
list_loved(limit) |
List all loved/hearted tracks [♥ 喜欢] |
search_loved(query) |
Search only within loved tracks |
list_playlists |
List all playlists |
list_history(limit) |
Recently played tracks |
history_search(query) |
Search within play history |
set_source(name) |
Switch source: apple_music | local | qq_music |
generate_profile(period) |
Generate listening report + open HTML in browser — daily | weekly | monthly | yearly |
focus_start(work, break_, cycles) |
Start Pomodoro focus session |
focus_status |
Current focus phase and time remaining |
focus_stop |
Stop focus session |
show_player |
Render pixel player UI |
show_cover |
Render current track cover art as pixel art |
show_lyrics |
Show karaoke / synced lyrics |
dj_say(message) |
Have DJ Buddy say something |
vibe_set(vibe) |
Set session vibe / mood |
status |
Full player state |
tips |
Show a card of natural-language phrases the user can say |
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.
- 4d ago First seen · 186 lines · 56 tokens per session scan C a9f530068dbb
cwb is a skill published in the GitHub repository jaychempan/coding-with-beat (114 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 2,641 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
audiocraft-audio-generation
AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.
image-generation
Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.
audio-cog
OpenSquilla-compatible audio generation adapter for webpage audio requests. Prefer OpenRouter config/API key in OpenSquilla; preserve the upstream CellCog workflow only as optional ClawHub provenance.
nano-banana-pro-openrouter
Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skillexec when a meta-skill needs local image files and structured IMAGEREADY records without spawning an LLM agent.
cli-inference
Use this skill when the user wants to run or debug MLX-VLM inference from the command line, including uv run mlxvlm.generate, image/audio/video inputs, local model paths, Hugging Face model IDs, deterministic repro commands, and CLI errors around processors, prompts, model loading, or missing weights.