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/hrygo/hotplex/hotplex-diagnosticsnpx skills add hrygo/hotplex --skill hotplex-diagnosticsgit clone --depth 1 https://github.com/hrygo/hotplexWhat 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 | $0.00059 | $0.00453 |
| Opus 5 | $0.00030 | $0.00227 |
| Sonnet 5 | $0.00012 | $0.00091 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
hotplex-diagnostics 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 2d 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 诊断
本 Skill 只授权读取和分析。诊断请求不授权修复、终止 Session、读取凭据、创建 Issue 或改变任何外部状态。需要受保护的 Admin 证据时，只使用已经获得授权的 Admin client 或用户提供的凭据上下文；不要读取或打印 token、cookie、完整环境文件 和私人 payload。
路由
- Gateway、Worker、Session、进程或日志异常：读取 runtime-diagnosis.md。
- Worker 仍在运行但用户收不到增量、流式反馈中断或疑似静默丢弃：再读取 feedback-chain.md。
- 仅需运行
hotplex status、doctor、security或config：改用hotplex-cli。 - 结论需要安装、更新、重启、配置写入或 Admin mutation 才能验证：停止诊断， 报告缺少的 operator 授权，不要自行转入修复。
证据原则
从用户症状开始，逐层缩小范围；优先使用当前安装版本的 --help、只读 CLI 和
只读 Admin 视图，再用日志、进程、只读数据库或源码补充。每个结论区分观测事实、
证据支持的推断和未验证假设。某层已经解释症状时停止，不为完成清单继续扩张范围。
输出应给出根因链、影响、证据和下一步；只报告实际执行的检查。若用户希望修复、 提交 Issue 或进行其他外部操作，先取得该具体动作的明确授权。
What ships with it
3 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.
- 2d ago First seen · 32 lines · 59 tokens per session scan A ce2e64241b02
hotplex-diagnostics is a skill published in the GitHub repository hrygo/hotplex (48 stars, last pushed 8d ago), licensed Apache-2.0. It adds 59 tokens to every session and 453 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
release-publish
Publish a new AlphaClaw release to npm and GitHub. Use when the user asks to cut a release, publish a version, write release notes, draft a release tweet, or close issues addressed in a release. Covers git history analysis, release note drafting, npm publishing, GitHub release creation, issue closing, and tweet…
release-analysis
Analyze an upstream product, dependency, or platform release for downstream impact on the current repo. Use when the user gives a package or repo name such as openclaw or GOG-CLI, or asks about release notes, changelogs, tags, dependency bumps, or upstream announcements. Resolve the GitHub repository, read the latest…
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.
release-beta
Publish the next AlphaClaw beta and always update the Railway beta template pin to the exact released beta version.
railway-volume-to-docker
Sync runtime data from a Railway deployment into local Docker for realistic testing. Use when the user asks to copy Railway data, clone production state locally, or test with real usage/session/config data.