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 inclusionAI/Avernet --skill bcs-coordinationgit clone --depth 1 https://github.com/inclusionAI/AvernetWrote 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/inclusionai/avernet/bcs-coordination)<a href="https://agentmods.dev/skills/inclusionai/avernet/bcs-coordination"><img src="https://agentmods.dev/badge/skills/inclusionai/avernet/bcs-coordination/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/inclusionai/avernet/bcs-coordination"><img src="https://agentmods.dev/badge/skills/inclusionai/avernet/bcs-coordination.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.03148 |
| Opus 5.5 | $0.00036 | $0.01259 |
| Sonnet 5.5 | $0.00018 | $0.00630 |
| Haiku 4.5 | $0.00009 | $0.00315 |
Grade A, and why
bcs-coordination scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BCS 多智能体协同和交互引擎 (Bot Coordination Service)
🎯 核心目标
本技能是处理所有多 Bot 协作场景的唯一入口。当遇到以下任一特征时,必须调用:
🏢 B2B / 生产力场景
- 能力边界突破:需引入外部专长(代码、法律、数据)。
- 信息/视角补全:打破信息孤岛,融合多方数据。
- 权限/资源隔离:跨系统、跨角色的代理操作。
- 冲突与共识:多方利益/观点不一致,需仲裁对齐。
- 自定义协作:自定义参与角色、执行节点、串并行关系和最终交付物。
🎮 2C / 消费与娱乐场景
- 互动游戏组局:跑团 (TRPG)、狼人杀、文字冒险游戏 (MUD),需要 DM (主持人) 和多个 NPC。
- 沉浸式角色扮演:用户与多个性格迥异的虚拟角色互动(如:家庭模拟、历史对话、粉丝见面会)。
- 创意内容共创:多人接龙写小说、头脑风暴、即兴喜剧表演。
- 情感陪伴矩阵:同时与多个不同人设的伴侣/朋友聊天,形成群体社交氛围。
- 教育与陪练:模拟面试、语言角对话、辩论赛对手。
运行前准备
本技能不安装内部依赖,也不假设公司网络。执行任何 BCS 命令前,先确认:
bcs-cli已安装并在PATH中- 保留运行环境已有的
BOT_DATA_DIR;未设置时优先使用当前 Bot 的OPENCLAW_DATA_DIR,最后才回退到单 Bot 默认目录$HOME/.openclaw - 正常 Bot Runtime 不传全局
--url,也不主动为BCS_API_BASE_URL填充 localhost 默认值
export BOT_DATA_DIR="${BOT_DATA_DIR:-${OPENCLAW_DATA_DIR:-$HOME/.openclaw}}"
bcs() {
BOT_DATA_DIR="$BOT_DATA_DIR" bcs-cli "$@"
}
不得把上述回退改写为 BOT_DATA_DIR="$HOME/.openclaw"。这种写法会覆盖 singlebox 等多 Bot 运行环境为当前 Bot 注入的隔离目录,导致使用其他 Bot 的身份。
bcs-cli 会从当前 $BOT_DATA_DIR/.bcs/session.json 的 api_base_url 或
bcs_url 发现服务地址,并把 ws / wss 转换为 http / https,同时去掉
WebSocket 连接路径(例如 /ws/bot)。只有用户明确指定地址或正在进行人工地址调试时,
才使用全局 --url 或覆盖已有的 BCS_API_BASE_URL。不得因为 localhost 端口不可用就判断
当前 Bot 未连接 BCS;先让 CLI 按当前 session 做地址发现并读取其真实结果。
认证与 Token
- 直接运行
bcs-cli,由 CLI 使用运行环境已有的BCN_BOT_TOKEN,或从当前$BOT_DATA_DIR/.bcs/session.json读取认证信息。 - 不主动查找、读取、复制、打印或拼接 token;不要创建
TOKEN、TOKEN2等临时变量。 - 不设置
BCN_BOT_TOKEN或BCS_BOT_TOKEN,也不传--token。只有用户明确要求人工调试并直接提供 token 时,才允许按用户指定方式覆盖。 - session 文件由 WebSocket channel 或
bcs connect管理。不要遍历其他 OpenClaw 目录寻找 session 文件。
正常 Bot 运行时只需保证 BOT_DATA_DIR 指向当前 Bot;认证发现由 CLI 完成,skill 不接触 token 内容。
命令执行方式
下文所有示例默认已经执行上述准备步骤,使用 bcs 作为保留当前 BOT_DATA_DIR、
且不覆盖 CLI 地址发现的 bcs-cli 简写:
建群和发现协作者时,BCS_BOT_UUID 表示当前 Bot 的真实 UUID:优先取运行环境的
BCN_BOT_UUID,未提供时只读取当前 $BOT_DATA_DIR/.bcs/session.json 的 bot_uuid
字段。不要读取或输出 token,也不要把示例中的 bot-dba 当作真实 ID;参与者应来自发现结果。
What ships with it
13 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.
- references/access-control.md 7.9 KB
- references/bot.md 7.4 KB
- references/collaboration-drafts.md 2.9 KB
- references/custom-collaboration-schema.md 18 KB
- references/custom-collaboration.md 13 KB
- references/fuse.md 5.0 KB
- references/group-context.md 12 KB
- references/group.md 17 KB
- references/network.md 5.2 KB
- references/service.md 3.9 KB
- references/session-file.md 5.5 KB
- references/session.md 8.8 KB
- test/test.md 981 B
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.
- 3d ago Changed · +17 lines 56217ddcbbb6
- 4d ago Changed · +1 lines 1f012867d874
- 1mo ago Changed · +1 lines · +5 tokens per session 30d015829651
- 1mo ago Changed 5fe8a60061ad
- 1mo ago First seen · 154 lines · 86 tokens per session scan A 8d8c4567c455
bcs-coordination is a skill published in the GitHub repository inclusionAI/Avernet (593 stars, last pushed today), licensed Apache-2.0. It adds 91 tokens to every session and 3,148 once invoked, about $0.0004 per session on Opus 5.5. 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
apps
Build and iterate on schema-backed Swarm Apps with live models, named queries, custom actions, and json-render interfaces using the app-upsert, app-get, app-list, and app-patch tools.
kapso-whatsapp
How to interact with Kapso WhatsApp from the swarm — read inbound webhook payloads (text AND media), fetch message history, send free-form messages within the 24h session window (and template messages outside it), mark-as-read, show the typing indicator, send reactions, download media, verify webhook signatures, and…
swarm-scripts
Bulk, repeat, fan-out, or data-heavy work: write and run swarm scripts (inline script-run, named script-upsert, durable launch-script-run). Covers the script-vs-tool rubric, the authoring contract (args first, ctx second), the seed catalog, connections and secrets, files and bash over the agent-fs drive (ctx.fs…
open-prompt-showreel
Make a design-led motion-graphics video (showreel, eval comparison, feature or bug-hunt story) from one open prompt. Claude Opus at max effort designs, codes and renders the whole thing itself in a scratch dir, with no template and no repo PR. Use for any "make a video for X" / "do a showreel for Y" / "a little…
composio
Use Composio from Agent Swarm through the agent-swarm x composio CLI route, the swarmx MCP tool, or a registered ctx.api.composio script connection. Trigger when a task needs connected third-party app tools such as Gmail, Google Calendar, Google Docs, Google Drive, GitHub, Slack, Notion, or HubSpot through Tool Router…
motion-design-video-analysis
Reverse-engineer a short motion-design / product-update video (animation technique, timing and easing, composition, transitions, likely tooling, vibe, audio) and produce a rebuild spec someone can build from. Default path is one call to google/gemini-3.8-flash over sampled frames, then a mandatory by-eye check of…