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 ooooooooooooooooooop/agent-tools --skill agent-switchboard-opsgit clone --depth 1 https://github.com/ooooooooooooooooooop/agent-toolsWrote 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/ooooooooooooooooooop/agent-tools/agent-switchboard-ops)<a href="https://agentmods.dev/skills/ooooooooooooooooooop/agent-tools/agent-switchboard-ops"><img src="https://agentmods.dev/badge/skills/ooooooooooooooooooop/agent-tools/agent-switchboard-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/ooooooooooooooooooop/agent-tools/agent-switchboard-ops"><img src="https://agentmods.dev/badge/skills/ooooooooooooooooooop/agent-tools/agent-switchboard-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 | $0.00160 | $0.06707 |
| Opus 5.5 | $0.00064 | $0.02683 |
| Sonnet 5.5 | $0.00032 | $0.01341 |
| Haiku 4.5 | $0.00016 | $0.00671 |
Grade A, and why
agent-switchboard-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 1mo 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Switchboard 运维手册
本 Skill 是使用 agent-switchboard MCP（本地跨 agent 协作桥）的操作契约，全部经验来自真实生产使用的事故与验收记录。只负责编排规则；任务本身的修改纪律交给 minimal-implementation，范围澄清交给 clarify-before-change。
适用范围与触发边界
触发边界：存在任一可用委派通道即可触发；随后按任务类型进入相应路由：
- 存在任一可用委派通道：
mcp__agent-switchboard__*工具，或宿主原生委派机制（如后台 subagent）； - 任务属于以下之一：跨模型委派（审查/实现/辩论）、受管长任务执行、监督或收取其他 agent 会话的成果、多窗口并行编排。
不适用场景
- 单会话可直接完成的小型或中型修改：不要为普通任务起 supervisor。
- 环境未安装 agent-switchboard 且也无原生委派通道：不要猜测工具名或要求用户临时安装，安装属于高风险操作，需用户明确授权。
- 纯只读问答：直接回答，不经 broker 绕道。
核心模式：管理者—执行者边界
- 会话管理者（你自己）只负责：定目标与阶段顺序、写完整派工提示词、审阅执行者证据、下返修指令、判定阶段是否通过、向用户汇报。
- 任务规模一律由
task-mode-router判级，不由"我已经在做了"反推：判为中型及以上的动手操作（调查、读大量文件、编码、改配置、跑构建/测试/数据扫描、Git 提交）委派给受管执行者；判为小型的单会话修改可直接最小修改并验证。执行前记录所选路由与理由（写入派工单或 broker 记录）。 - 管理者允许做有界、只读的独立验收：复跑只读校验脚本、
git show/git diff --check、读文件核对哈希/行号/输出。禁止实现、提交、扩大调查范围。 - 执行者自报的 PASS 不是验收依据；验收以独立证据为准（上述只读核验的结果）。
- 互不冲突的任务应主动并行多个受管窗口，无需用户提醒；存在同一文件或同一数据冲突风险的任务在同一窗口排队。
- 执行者窗口验收完成或确认不再需要后立即
close_supervisor/stop_managed_claude_supervisor，不得长期悬挂闲置窗口。
路由规则：确定性选择委派通道
按以下顺序判定，命中即停；执行前记录所选路由与理由：
- 小型任务直接执行：经
task-mode-router判级为小型的单会话修改，不走任何委派，直接最小修改并验证。 - 同厂劳动 native subagent 优先：与当前会话同厂（同厂商/同宿主）的执行类劳动，优先使用宿主原生委派机制（如后台 subagent）。这不是"switchboard 失败后的降级"，而是 broker 自身要求的默认路由。
- 异厂咨询/审查走 switchboard：跨厂商模型的审查、评审、辩论、咨询，经
route_agent_task/consult_*/queue_*_request走 broker。 - 受管 Claude 长任务走 supervisor：需要跨多轮、可归档续接的 Claude 长任务，用
start_managed_claude_supervisor受管执行。 - 逐级降级：所需路由的真实调用失败时，才降级到下一可用通道（switchboard → 原生 subagent → 直接执行），并记录降级原因。可用性以真实调用为准：工具未出现在会话声明目录里不等于不可用（热重载可能迟注册），禁止凭目录清单下"无法使用"的结论。
- 无可用执行者报 BLOCKED：所有通道均不可用时，在验收报告中报 BLOCKED，说明已试通道与失败原因，不硬撑执行。
用户成本偏好：计费 token 与订阅额度并存时，在任务适配、真实可用性和授权边界均满足的前提下优先 MCP 路由（省钱）；不得以此绕过最小权限、认证失败停机或破坏性操作上报规则。
降级通道的能力差异要如实告知用户：宿主 subagent 没有 broker 的事件流、归档和跨会话续接能力；长任务可建议用户安装 agent-switchboard（安装属高风险操作，需明确授权）。
统一监督协议（2026-08-26 沉淀，业界对照联网验证）
受管 supervisor 与 DSH 会话（goal 模式）是两套执行引擎，但应共用一套监督协议—— 业界共识（Langfuse/LangSmith/OTel/Temporal）：观测平台只负责记录，"每个执行器都必须 适配同一组事件与状态字段"，而不是为每个执行器发明一套监督方式。 来源：https://langfuse.com/docs/observability/data-model、 https://docs.langchain.com/langsmith/annotate-code、 https://github.com/open-telemetry/semantic-conventions-genai/blob/main/docs/gen-ai/gen-ai-agent-spans.md、 https://github.com/temporalio/documentation/blob/main/docs/develop/go/activities/timeouts.mdx
What ships with it
6 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.
- 1mo ago First seen · 199 lines · 160 tokens per session scan A 682e253ee03a
agent-switchboard-ops is a skill published in the GitHub repository ooooooooooooooooooop/agent-tools (3 stars, last pushed 1mo ago), licensed MIT. It adds 160 tokens to every session and 6,707 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
analyze
Analyze a legacy app in any language before rewriting it in Elixir: inventory, features as goals, why each mechanism exists, runtime topology, external contracts. Use to start or refresh a rewrite.
session-deep-dive
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
brainstorm
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.
plugin-dev-workflow
Guide plugin development workflow — editing skills, agents, hooks, or eval framework in this repo. Use when modifying files in plugins/elixir-phoenix/, lab/eval/, or lab/autoresearch/. Ensures changes pass eval, lint, and tests before committing.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.