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 skills add LSTM-Kirigaya/openclaw-onebot --skill onebot-opsgit clone --depth 1 https://github.com/LSTM-Kirigaya/openclaw-onebotWrote 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/lstm-kirigaya/openclaw-onebot/onebot-ops)<a href="https://agentmods.dev/skills/lstm-kirigaya/openclaw-onebot/onebot-ops"><img src="https://agentmods.dev/badge/skills/lstm-kirigaya/openclaw-onebot/onebot-ops/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/skills/lstm-kirigaya/openclaw-onebot/onebot-ops"><img src="https://agentmods.dev/badge/skills/lstm-kirigaya/openclaw-onebot/onebot-ops.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 | $0.00039 | $0.00863 |
| Opus 5 | $0.00019 | $0.00432 |
| Sonnet 5 | $0.00008 | $0.00173 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
onebot-ops 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 10d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OneBot 运维/使用规范
OneBot v11 协议渠道，支持 QQ/Lagrange.Core/go-cqhttp。消息收发均通过 Channel 的 outbound 与 deliver 完成，不依赖 Agent 工具。
快速判断
| 场景 | 说明 |
|---|---|
| 接收消息 | 私聊全回复，群聊默认仅 @ 回复，详见 receive.md |
| message 工具 target | 群聊必须用 ctx.To（格式 group:群号），勿用 SenderId |
| 发送消息 | 使用 openclaw message send CLI，详见 send.md |
| 配置 | 运行 openclaw onebot setup 或编辑 openclaw.json，详见 config.md |
插件安装
openclaw plugins install @openclaw/onebot
本地开发时：
openclaw plugins install ./openclaw-onebot
前置条件
- Gateway 已启动：
openclaw gateway - OneBot 实现（Lagrange.Core / go-cqhttp）已运行并暴露 WebSocket
- 在
openclaw.json中配置channels.onebot或通过ONEBOT_WS_*环境变量
OneBot 协议能力
对应 Lagrange.onebot context.ts 的 API：
| 能力 | 说明 |
|---|---|
| send_private_msg | 发送私聊消息 |
| send_group_msg | 发送群消息 |
| send_msg | 按 message_type 发送 |
| 图片消息 | message 为 [{ type: "image", data: { file } }] |
| delete_msg | 撤回消息 |
| get_msg | 获取单条消息 |
| get_group_msg_history | 获取群历史（Lagrange.Core 扩展），支持 reverse_order 分页 |
| upload_group_file | 上传群文件 |
| upload_private_file | 上传私聊文件 |
| set_msg_emoji_like | 表情回应（Lagrange/QQ NT 扩展） |
Agent 工具与 CLI
插件提供群历史、按名字搜 QQ 等能力，既注册为 Agent 工具（供 Cron/脚本/AI 调用），也提供等价的 CLI 命令，便于 AI 与人工按文档调用。
详细说明与所有命令用法见：agent-tools.md
常用 CLI 一览
| 命令 | 说明 |
|---|---|
openclaw onebot setup |
交互式配置 OneBot 连接 |
openclaw onebot get-group-msg-history --group-id <群号> [--hours N] |
获取群历史（单页或最近 N 小时内，从旧到新） |
openclaw onebot search-group-member --group-id <群号> --name <名字> |
按名字模糊搜群友 QQ 号 |
openclaw onebot upload-file --target group:<群号> --file <路径> --name <文件名> |
上传文件到群/私聊 |
openclaw message send --channel onebot --target group:xxx --message "hi" |
发送文本/图片 |
openclaw gateway status |
查看 Gateway 状态 |
openclaw logs --follow |
查看日志 |
AI 或脚本需要「获取群历史、查群友 QQ」时，应使用上述 CLI 或查阅 agent-tools.md 中的完整参数说明。
What ships with it
4 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.
- 10d ago First seen · 73 lines · 39 tokens per session scan A 052c3dbfba8d
onebot-ops is a skill published in the GitHub repository LSTM-Kirigaya/openclaw-onebot (143 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 863 once invoked, about $0.0002 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
clawteam
Multi-agent swarm orchestration. USE THIS (not delegatetask) when the user says team/swarm/multi-agent/clawteam/parallel-agents/agent-team, or asks for multi-perspective analysis (stocks, research, code review, strategy). Spawns N Hermes workers in tmux windows with git worktree isolation, file-based inboxes, and a…
clawteam
Multi-agent swarm coordination via the ClawTeam CLI. Use when the user wants to create agent teams, spawn multiple agents to work in parallel, coordinate tasks with dependencies, broadcast messages between agents, monitor progress via kanban board, or launch pre-built team templates (hedge-fund, code-review…
openclaw-plugin
This plugin is a thin adapter between OpenClaw and LycheeMem. It does not replace memory-core, does not claim plugins.slots.memory, and does not duplicate LycheeMem algorithms.
lycheemem
Forceful operating rules for using LycheeMem as the primary structured long-term memory path inside OpenClaw.
memory
Use LycheeMem as Claude Code's structured long-term memory for prior conversations, user preferences, project decisions, timelines, and durable facts.
tweetclaw
OpenClaw guide for Twitter search, follower exports, monitoring, media, and approved X automation through Xquik. Not affiliated with X Corp.