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 instructions/jaychempan/coding-with-beat/claude-mdgit 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/instructions/jaychempan/coding-with-beat/claude-md)<a href="https://agentmods.dev/instructions/jaychempan/coding-with-beat/claude-md"><img src="https://agentmods.dev/badge/instructions/jaychempan/coding-with-beat/claude-md.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 | $0.00237 | $0.00237 |
| Opus 5 | $0.00118 | $0.00118 |
| Sonnet 5 | $0.00047 | $0.00047 |
| Haiku 4.5 | $0.00024 | $0.00024 |
Grade A, and why
coding-with-beat CLAUDE.md 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 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.
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.
What it actually says
Coding With Beat
Music intent
When the user asks for music by mood, scene, or style description
(e.g. "来首轻松的", "something for late-night coding", "带点爵士的"),
use smart_search() instead of search().
Use search() only when the user provides a specific track title,
artist name, or album title.
Smart search: multi-angle display
When handling a mood/vibe/scene music request, call smart_search() once with
the queries parameter containing 2–3 keyword angles. Do NOT call smart_search()
multiple times — each call overwrites the queue, so play_number() will index into
the wrong results.
Example for "深夜写代码":
smart_search(queries=[
"lofi hip hop late night coding instrumental",
"lofi jazz late night rain cozy",
"synthwave retrowave night drive electronic",
])
The tool returns globally numbered results grouped by direction with emoji labels.
Ask the user to pick by number and call play_number(N). Do NOT auto-play.
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 · 31 lines · 237 tokens per session scan A b4b8e66bf753
coding-with-beat CLAUDE.md is an instructions file published in the GitHub repository jaychempan/coding-with-beat (114 stars, last pushed 2mo ago), licensed MIT. It adds 237 tokens to every session, about $0.0012 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.
Other instructions, from other repositories
FableCut CLAUDE.md
Claude Code instructions for ronak-create/FableCut, covering fablecut — browser video editor, drivable by claude code, token-efficient editing (important for agents), where the files are, run and how claude code edits a video.
dcc-mcp-blender CLAUDE.md
Instructions for dcc-mcp/dcc-mcp-blender, covering what this project does, claude desktop configuration, progressive loading — important for claude, claude-specific tips and quick test prompts.
dcc-mcp-blender GEMINI.md
Instructions for dcc-mcp/dcc-mcp-blender, covering gemini.md — google gemini / vertex ai integration guide, what this project does, gemini-specific strengths, 1. skill script generation and 2. structured tool results.
pydantic-ai CLAUDE.md
Claude Code instructions for pydantic/pydantic-ai, a project described as: How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.