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/guillermoscript/lms-front/claude-soundsnpx skills add guillermoscript/lms-front --skill claude-soundsgit clone --depth 1 https://github.com/guillermoscript/lms-frontWrote 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/guillermoscript/lms-front/claude-sounds)<a href="https://agentmods.dev/skills/guillermoscript/lms-front/claude-sounds"><img src="https://agentmods.dev/badge/skills/guillermoscript/lms-front/claude-sounds.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 | $0.00094 | $0.02063 |
| Opus 5 | $0.00047 | $0.01032 |
| Sonnet 5 | $0.00019 | $0.00413 |
| Haiku 4.5 | $0.00009 | $0.00206 |
Grade D, and why
claude-sounds scanned grade D with 3 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 5d 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 -fsSL https://raw.githubusercontent.com/guillermoscript/agent-skills/main/skills/claude-sounds/install.sh | bash Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `~/.claude/settings.json` | hook entries (merged, never replaced) | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/guillermoscript/agent-skills/main/skills/claude-sounds/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-sounds — hear what just happened
Ambient awareness for long runs. Walk away from the terminal and still know whether it landed, died, or is waiting on you — and, for turn endings, roughly how big the change was.
Install
curl -fsSL https://raw.githubusercontent.com/guillermoscript/agent-skills/main/skills/claude-sounds/install.sh | bash
Pick a pack while installing:
curl -fsSL .../install.sh | bash -s -- --pack zelda
Then restart Claude Code, or open /hooks once — the settings watcher does
not pick up a new hook mid-session. This is the most common reason it seems not
to work.
Requires jq, curl, and an audio player (afplay ships with macOS; mpv,
ffplay, mpg123 or paplay on Linux).
The installer also drops the /sound-setup wizard into
~/.claude/skills/sound-setup/, so customizing works straight after a curl
install with no extra step.
Flags: --pack <name>, --uninstall, --no-sounds (hook only, spoken
fallbacks), --no-git (turn-end sounds only), --no-skill (skip the wizard),
--dry-run, --yes.
What plays when
When a turn ends, scaled by lines written or edited in that turn (Write
content + Edit new_string, counted only since the last user prompt):
| Lines | Event | tiktok | zelda | mario |
|---|---|---|---|---|
| <50 | done_tiny |
vine boom | rupee | coin |
| 50+ | done_small |
FAAAH | korok | 1-up |
| 200+ | done_medium |
Faaaa | secret jingle | 1-up mushroom |
| 500+ | done_big |
boosted FAAAH | item catch | extra life |
| 1000+ | done_epic |
I GOT THIS FAAAAAHHHH | high-value item | course clear |
Status comes from the last assistant message. The three background-job markers are exact; the rest is a heuristic.
| Trigger | Event |
|---|---|
contains result: |
completed → one of the five above |
contains needs input:, or ends with ? |
needs_input |
contains failed:, or error keywords |
failed (failed_big over 200 lines) |
| anything else | other |
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 203 lines · 94 tokens per session scan D 3bfd49e4cf01
claude-sounds is a skill published in the GitHub repository guillermoscript/lms-front (25 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 2,063 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, 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
api-development
FastGPT API 开发规范。重点强调使用 zod schema 定义入参和出参,在 API 文档中声明路由信息,编写对应的 OpenAPI 文档,以及在 API 路由中使用 schema.parse 进行验证。.
ci-workflow-sync
FastGPT CI workflow 双轨同步。当用户修改或新增 .github/workflows/ 下的 GitHub Actions workflow 时必须触发：同步更新 .forgejo/workflows/ 对应文件保持功能一致，或判断是否需要新建 Forgejo 版本。涉及 CI、GitHub Actions、Forgejo Actions、镜像构建、container registry、artifact、workflow yaml 改动、build- workflow、test- workflow 时也使用此技能。即使用户只提到"改一下 CI"或"加个 workflow"也应触发。.
system-migration-development
为 FastGPT 新增、修改或审查自动系统升级脚本及其注册信息。涉及系统迁移、升级任务、启动迁移、migration registry、checkpoint、全量重跑、阻塞升级、进度或失败数据时使用；普通业务更新和未接入自动升级框架的一次性手工清洗不使用。.
deprecate-workflow-node
当用户需要弃用一个工作流节点（保留向后兼容、隐藏出模板面板）时触发该 skill。FastGPT 工作流节点的弃用流程标准化封装，覆盖模板、Dispatcher、UI 引用等所有需要改动的位置。.
prompt-optimize
Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue. Activates when user asks to "optimize prompt", "improve system instruction", "enhance AI instruction", or mentions prompt engineering tasks.
doc-i18n
将 FastGPT 文档从中文翻译为面向北美用户的英文。当用户提到翻译文档、i18n、国际化、translate docs、新增/修改了中文文档需要同步英文版时，使用此 skill。也适用于用户要求检查文档翻译缺失、批量翻译、或对比中英文文档差异的场景。.