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.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.02585 |
| Opus 5 | $0.00043 | $0.01293 |
| Sonnet 5 | $0.00017 | $0.00517 |
| Haiku 4.5 | $0.00009 | $0.00259 |
Grade A, and why
bcs-coordination scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BCS 多智能体协同和交互引擎 (Bot Coordination Service)
🎯 核心目标
本技能是处理所有多 Bot 协作场景的唯一入口。当遇到以下任一特征时,必须调用:
🏢 B2B / 生产力场景
- 能力边界突破:需引入外部专长(代码、法律、数据)。
- 信息/视角补全:打破信息孤岛,融合多方数据。
- 权限/资源隔离:跨系统、跨角色的代理操作。
- 冲突与共识:多方利益/观点不一致,需仲裁对齐。
- 自定义协作:自定义参与角色、执行节点、串并行关系和最终交付物。
🎮 2C / 消费与娱乐场景
- 互动游戏组局:跑团 (TRPG)、狼人杀、文字冒险游戏 (MUD),需要 DM (主持人) 和多个 NPC。
- 沉浸式角色扮演:用户与多个性格迥异的虚拟角色互动(如:家庭模拟、历史对话、粉丝见面会)。
- 创意内容共创:多人接龙写小说、头脑风暴、即兴喜剧表演。
- 情感陪伴矩阵:同时与多个不同人设的伴侣/朋友聊天,形成群体社交氛围。
- 教育与陪练:模拟面试、语言角对话、辩论赛对手。
运行前准备
本技能不安装内部依赖,也不假设公司网络。执行任何 BCS 命令前,先确认:
bcs-cli已安装并在PATH中- 保留运行环境已有的
BOT_DATA_DIR;未设置时优先使用当前 Bot 的OPENCLAW_DATA_DIR,最后才回退到单 Bot 默认目录$HOME/.openclaw BCS_API_BASE_URL指向 BCS HTTP API;未设置时使用本地默认http://127.0.0.1:21000
export BOT_DATA_DIR="${BOT_DATA_DIR:-${OPENCLAW_DATA_DIR:-$HOME/.openclaw}}"
export BCS_API_BASE_URL="${BCS_API_BASE_URL:-http://127.0.0.1:21000}"
bcs() {
BOT_DATA_DIR="$BOT_DATA_DIR" bcs-cli --url "$BCS_API_BASE_URL" "$@"
}
不得把上述回退改写为 BOT_DATA_DIR="$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。
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$BOT_DATA_DIR/.bcs/session.json读取认证信息。 - 不主动查找、读取、复制、打印或拼接 token;不要创建
TOKEN、TOKEN2等临时变量。 - 不设置
BCN_BOT_TOKEN或BCS_BOT_TOKEN,也不传--token。只有用户明确要求人工调试并直接提供 token 时,才允许按用户指定方式覆盖。 - session 文件由 WebSocket channel 或
bcs connect管理。不要遍历其他 OpenClaw 目录寻找 session 文件。
正常 Bot 运行时只需保证 BOT_DATA_DIR 指向当前 Bot;认证发现由 CLI 完成,skill 不接触 token 内容。
命令执行方式
下文所有示例默认已经执行上述准备步骤,使用 bcs 作为 bcs-cli --url "$BCS_API_BASE_URL" 的简写:
bcs health
bcs list
bcs request-group-help --topic "数据库死锁排查,需要DBA专家"
bcs collaboration validate /path/to/workflow.yaml
bcs collaborate permission --session "$current_bcs_session_id"
若不使用 shell 函数,等价写法为:
BOT_DATA_DIR="$BOT_DATA_DIR" bcs-cli --url "$BCS_API_BASE_URL" health
场景指南
收到请求后请按照以下步骤执行:
- 分析请求,按照需求判断场景,读取
references/目录下对应的参考文档 - 根据参考文档处理用户请求
- 返回结果
What ships with it
11 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 7.8 KB
- references/bot.md 6.6 KB
- references/custom-collaboration-schema.md 9.5 KB
- references/custom-collaboration.md 9.4 KB
- references/fuse.md 4.7 KB
- references/group.md 18 KB
- references/network.md 4.8 KB
- references/service.md 3.9 KB
- references/session-file.md 5.5 KB
- references/session.md 8.1 KB
- test/test.md 537 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.
- 9d ago First seen · 154 lines · 86 tokens per session scan A 8d8c4567c455
bcs-coordination is a skill published in the GitHub repository inclusionAI/Avernet (536 stars, last pushed today), licensed Apache-2.0. It adds 86 tokens to every session and 2,585 once invoked, about $0.0004 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
coordinate-agents
Route Codex-native multi-agent orchestration in a Git repository through a local-first, recoverable Agent Bus. Use for role-based planning, task execution, review, recovery, adapters, and human-gated release workflows. The plugin supports Codex CLI, Google Antigravity CLI, Claude, and other configured coding agents.…
coordinate-task
Run a Coordinate Agents Task from requirement clarification through planning, implementation, review, and the human release gate. Hide Agent Bus transport details behind the durable Task API.
coordinate-recover
Diagnose and safely resume Coordinate Agents Tasks after executable failure, non-zero exit, timeout, stale claim, processing message, or Implementer ERROR. Recovery is explicit and never an automatic retry loop.
coordinate-setup
Discover coding CLIs on the current computer and configure a Coordinate Agents implementation agent. Use for setup, executable checks, registered agents, user-level configuration, and project-over-user precedence.
coordinate-review
Review a Coordinate Agents implementation as the Codex Reviewer. Verify the real commit, diff, tests, validation evidence, and specification without modifying the Implementer's product code.
deliberated-review
Review code with multiple specialist subagents, then use gemot to find where they disagree and why. Requires gemot MCP server configured.