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.
git 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/commands/jaychempan/coding-with-beat/cwb)<a href="https://agentmods.dev/commands/jaychempan/coding-with-beat/cwb"><img src="https://agentmods.dev/badge/commands/jaychempan/coding-with-beat/cwb/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/jaychempan/coding-with-beat/cwb"><img src="https://agentmods.dev/badge/commands/jaychempan/coding-with-beat/cwb.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00037 | $0.02738 |
| Opus 5.5 | $0.00015 | $0.01095 |
| Sonnet 5.5 | $0.00007 | $0.00548 |
| Haiku 4.5 | $0.00004 | $0.00274 |
Grade A, and why
cwb 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
If the coding-with-beat UserPromptExpansion hook is installed, this command is handled by a private one-shot headless Claude session. The child session interprets the intent, runs a validated coding-with-beat action, returns a short result, and blocks this fallback prompt so the main conversation context stays clean.
You are driving the local coding-with-beat music player via its globally-installed CLI. Do NOT call any MCP tools — they may not be loaded. Always shell out via Bash to the cwb command (installed by install.sh at ~/.local/bin/coding-with-beat, backed by a venv at ~/.coding-with-beat/venv).
User intent: $ARGUMENTS
How to interpret
Parse the intent and pick exactly ONE action. If empty or ambiguous, default to status.
| Intent keywords | Command |
|---|---|
play/start + <query> |
cwb play <query> |
| play/resume with no query | cwb play |
| resume/继续/恢复 (after interruption) | cwb resume |
search/find/搜索/找 + <query> |
cwb search <query> |
| list/library/资料库/列表 | cwb list |
| pause/stop | cwb pause |
| next/skip | cwb next |
| previous/back | cwb prev |
| source/music source + `<apple_music | qq_music |
| like/favorite current | cwb like |
| shuffle/sequential/repeat | `cwb mode <shuffle |
| now playing/what's playing | cwb np |
| show player/player | cwb player |
| status | cwb status |
| lyrics/karaoke | cwb karaoke |
| anything else (mood, scene, vibe, free-form description) | multi-angle smart search (see below) |
Routing rule: if the argument does NOT start with one of the fixed verbs above (play, search, list, pause, next, prev, source, like, mode, np, player, status, karaoke, resume), treat the entire argument as a mood/scene description and run multi-angle smart search.
For search or play-by-query, the <query> is the rest of the text after the verb (artist name, song name, mood — pass it through verbatim, including Chinese). Quote it.
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.
- 1mo ago First seen · 191 lines · 37 tokens per session scan A 2b0de0dba47c
cwb is a command published in the GitHub repository jaychempan/coding-with-beat (113 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 2,738 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other commands, from other repositories
atomic-plan
Write a design doc (concepts, business rules, approaches) and a checkpoint-table spec (contract) for non-trivial work; inline spec only for trivial. Gauges triviality; loops spec authoring with subagents. Human-facing artifact, Mermaid diagrams allowed.
setup
Set up Duel Agents routing with your Duel API key.
config
View or edit DevSquad delegation preferences without re-running onboarding.
setup
A setup command for configuring claude-mini-hud as Claude Code's terminal status line. It lets the user choose Chinese, English, minimal, or ultra-minimal display text and writes the setting to Claude Code's configuration.
modernize-extract-rules
Mine business logic from legacy code into testable, human-readable rule specifications.
cc-probeline-update
Update cc-probeline to the latest release (or install it if missing), using the right channel for this OS.