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 hxy91819/mason-skills --skill bb-model-routinggit clone --depth 1 https://github.com/hxy91819/mason-skillsWrote 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/hxy91819/mason-skills/bb-model-routing)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/bb-model-routing"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/bb-model-routing/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/hxy91819/mason-skills/bb-model-routing"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/bb-model-routing.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 | $0.00045 | $0.01121 |
| Opus 5 | $0.00023 | $0.00561 |
| Sonnet 5 | $0.00009 | $0.00224 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
bb-model-routing 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 today.
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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BB 任务派发
本技能默认仅显式触发,使用 $bb-model-routing 调用。
为用户已要求的任务调用 scripts/bb-dispatch。工具别名、模型、推理级别和环境映射以用户配置为准;首次配置或调整映射时读取 配置与派发,使用其中的配置模板。参数细节查 bb-dispatch --help。
判断与调用
simple:局部改动,步骤与验收清楚。medium:范围明确,涉及少量模块或需要比较方案。complex:跨模块设计、根因难定位或较多不确定性。- 排查问题、找 bug 额外传
--kind debug,即使任务简单也保留该类型。 - 专门做测试验证、单测编写或执行验证额外传
--kind test。
bb-dispatch --difficulty medium --kind debug --task '<任务目标、范围与验收要求>'
bb-dispatch --difficulty medium --kind test --task '<测试目标、范围与验收要求>'
--task 只写任务目标、范围、输入和验收要求。provider、模型、推理级别和可用性检查是派发元数据:由 bb-dispatch 根据配置和目录决定,不写入子线程 prompt,也不要求子 agent 在开始前重新查询或确认。用户明确指定 provider 或模型时,将该要求映射到配置别名或配置调整,仍不把路由要求带入 --task。
用户指定工具别名或已有对应工具上下文时用 --agent <配置别名>,别名由用户配置定义,不推断本机已安装哪些工具。只有用户明确指定推理级别时才传 --reasoning;其余由脚本读取配置。配置未指定时省略该参数,使用 provider 默认值。命令未安装时直接执行本技能的 scripts/bb-dispatch。需要预览用 --dry-run,脚本已完成的环境与模型校验无需重复查询。
派发边界
所有 provider、模型、推理级别和默认路由均来自用户配置;脚本在创建前完成相应目录校验。父 agent 只负责选择任务难度、类型和配置别名,不能把路由选择或二次校验职责下放给子 agent。首次使用先按参考文档查询目标环境,再填写配置。缺少配置时完成配置准备,校验通过后再派发。
路由不可用或额度耗尽时报告原因;仅使用用户明确选择的替代配置别名,不内置渠道优先级或自动切换。
权限须符合任务授权;配置缺失或校验失败时说明缺口,不静默换模型或升权。
并发任务可能产生修改冲突时,可以使用 use-worktree 隔离;无冲突时沿用当前环境。操作前检查分支、工作区和 worktree,遵守用户授权。隔离环境准备好后用 --environment 指定,脚本只使用已有 BB 环境。
派发标题由脚本统一加 [Agent] 前缀;需要简短标题时传 --title,省略时从任务文本截取。
根据返回结果报告线程 ID、实际选择和状态。创建成功不代表任务完成;创建结果不明时先查询线程,避免重复派发。
作为编排后端
large-task-orchestrator 的确定性 driver 通过本技能派 Worker、Validator 与异常时的 Judge:Worker 按
能力档映射为 --difficulty,Validator 固定 --difficulty simple --kind test,Judge 固定 --difficulty complex --kind judge。
driver 只传任务文本、难度、类型与已有环境,路由仍由本配置决定;状态机、wait/output/tell 兼容性见其
references/bb-dispatch-loop.md。
defaults.test 决定 Validator 路由,defaults.judge 单独决定 Judge 路由,Worker 使用难度路由或
debug 路由。agents.<别名>.routes 按角色、难度和 default 项配置模型与 reasoning,选择规则见
配置与派发。
可观测性
使用 --dry-run 只读检查当前选择、目标环境和启动参数;派发返回实际选择与原始创建回执。当前没有持久运行历史、裁决回写或跨运行聚合,无法统计长期成功率;故障定位依赖返回错误和 BB 线程记录。
What ships with it
5 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.
- today Changed · +2 lines a69a115f3dbe
- yesterday Changed · +1 lines 930b92562f1c
- 2d ago Changed · +10 lines 442e7b286124
- 3d ago Changed · +2 lines 150e6249c524
- 4d ago First seen · 45 lines · 45 tokens per session scan A 2bc486fbcac9
bb-model-routing is a skill published in the GitHub repository hxy91819/mason-skills (2 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 1,121 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 2026-09-08.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.