Borrowing it
Nothing to install: this file belongs to hrygo/hotplex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hrygo/hotplex/main/.agents/skills/hotplex-stt-tts/SKILL.mdgit clone --depth 1 https://github.com/hrygo/hotplexWrote 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/hrygo/hotplex/hotplex-stt-tts)<a href="https://agentmods.dev/skills/hrygo/hotplex/hotplex-stt-tts"><img src="https://agentmods.dev/badge/skills/hrygo/hotplex/hotplex-stt-tts.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 | $0.00065 | $0.00739 |
| Opus 5 | $0.00032 | $0.00369 |
| Sonnet 5 | $0.00013 | $0.00148 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
hotplex-stt-tts 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 7d 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
HotPlex STT/TTS
当 HotPlex 报告缺少 funasr_onnx、MOSS 依赖/模型，或用户明确要求初始化、修复本地语音运行时时使用本 Skill。
这是 operator 流程。安装包、下载模型、修改 .env/config 和重启服务都属于变更；只有用户明确授权对应范围时才能执行。不要暴露凭据、完整环境文件或私有模型/cache 元数据。
详细流程见 references/initialization.md，修改主机前必须先读取。
范围
- STT：HotPlex
local或feishu+local，使用funasr-onnx和 SenseVoiceSmall。 - TTS：HotPlex
moss或edge+moss，使用 MOSS-TTS-Nano ONNX sidecar。 - 验收：依赖导入、模型资产、MOSS warmup、
hotplex doctor、Gateway 健康度和已配置消息渠道连接。
不要用本 Skill 修改语音功能代码、任意清理 Python 环境、泛化选择模型，或在没有初始化/修复请求时进行只读诊断。
操作规则
- 变更前检查已安装 CLI 帮助和当前配置。保留现有 provider、凭据、用户文件和无关环境变量。
- 优先在当前 HotPlex home 下使用专用 venv。HotPlex checker 和 MOSS 进程通过
PATH解析python3；必须验证同一个解释器能看到全部依赖。不要假设指向 venv 解释器的软链接能保留 venv 识别。 - 模型使用 reference 列出的官方 ModelScope 仓库；sidecar 脚本使用官方 MOSS 源码仓库。不要使用管道式 shell 安装器、未经审核的镜像或任意模型文件。
- 只做最小配置变更。重启前先验证配置；已安装服务使用原子命令
hotplex service restart，不要拆成手工 stop/start。 - 安装成功不等于任务完成：执行验收清单，并分别报告通过、警告、失败和有意未修改的状态。
完成标准
只有所有请求的运行时检查通过，或存在已记录的外部阻塞时，任务才可结束。至少验证：
- HotPlex 实际调用的解释器可以导入
funasr_onnx、onnxruntime和onnx。 - SenseVoiceSmall 资产存在，或已配置 cache 可以解析它们。
- MOSS TTS 和 codec ONNX 资产完整，localhost 冒烟测试中
/api/warmup-status达到ready。 hotplex doctor --json没有与请求相关的 STT/TTS/AgentConfig failure。- 任何重启后 Gateway 和用户请求的消息渠道仍然健康。
What ships with it
2 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.
- 7d ago First seen · 39 lines · 65 tokens per session scan A bda269729c7e
hotplex-stt-tts is a skill published in the GitHub repository hrygo/hotplex (49 stars, last pushed yesterday), licensed Apache-2.0. It adds 65 tokens to every session and 739 once invoked, about $0.0003 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 skills, from other repositories
reversi-master
One-click install + model switch:Claude Code,Codex CLI (OpenAI), Grok Build (xAI), DeepSeek Harness, Kimi Code (Moonshot) ,Qwen Code,Aider,OpenCode,MiMo Code (Xiaomi),ZCode (Z.AI),OpenClaw,Pi,OpenScience,Vibe-Trading,Claude Desktop (3P profile),ChatGPT desktop,OpenCode Desktop.
Trash Talk
AI becomes provocative and mocks the opponent during gameplay.
dreaming
Maintain Signet's living ontology and memory substrate from transcripts, memory artifacts, source artifacts, notes, summaries, and imported records.
signet-recall
Use Signet-specific recall and source search from Codex without confusing it with Codex native memory.
signet-ontology
Navigate Signet ontology and knowledge graph state from Codex.
signet-save-note
Save explicit notes into Codex native memory through Signet.