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 | $0.00114 | $0.05805 |
| Opus 5.5 | $0.00046 | $0.02322 |
| Sonnet 5.5 | $0.00023 | $0.01161 |
| Haiku 4.5 | $0.00011 | $0.00581 |
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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BB 任务派发
派发入口
Agent 自行决定使用 subagent，或用户只要求“用 subagent 检查一下”时，沿用宿主默认机制。查看或继续已有线程沿用现有上下文。
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。派发前确认配置文件存在，bb-dispatch 报“无法读取配置”时也先核对该路径：文件确实不存在才进入 bootstrap，按首次配置引导边汇报进度边检测可用 provider 与模型，给出建议配置，经用户确认后写入并 dry-run 验证，再回到派发；文件存在但读不了是配置损坏，报告并修复，不新建覆盖。调整已有映射时读取配置与派发。参数细节查 bb-dispatch --help。
判断与调用
难度只量一件事：任务的不确定性，即子线程开工时还不知道、必须自己弄清或裁决的东西。工作量、文件数、测试数、任务描述篇幅、“需要完整验证”，以及风险高低、缺陷级别、操作哪个环境、任务多重要、预算多宽，都在这个维度之外：当前模型能可靠执行高风险操作，风险由任务里的授权范围和审查规则控制。
每个任务单独判断，同一批任务也逐个归档：
-
用一句话说出任务的最大未知：按父 agent 掌握的实际情况，子线程拿到任务时还不知道、必须自己弄清或裁决的那件事。
-
按最大未知归档。默认派
simple。拿不准时把最大未知说得更具体再对照，仍落在两档之间就取低一档：simple：子线程能在已写明的范围内做完。说不出还要裁决的未知时归这里：做什么、改哪里、怎么算完成都已写进任务文本，失败了就修到测试通过。有边界、父线程不必先消化掉的未知也归这里：要回答的问题已经圈定的调研或设计；缺陷可复现、范围已圈定到某条链路或几个模块，根因尚未定位；按既定流程，或第一次跑但有备份或回滚手段的部署、发布与合并。典型还有按明确说明实现功能（代码量可以很大）、编写或执行既有测试、机械迁移、同步文档与配置。medium：只留给三类，不因工作量、风险或“还有未知”升档。(1) 同一任务的simple失败、反复返工或产出需要大量纠正，用--escalate-from升档重派。(2) 测试通过不等于做对：并发、锁与崩溃恢复；租户或安全隔离边界；发布签字，以及当必审改动的唯一审查人。(3) 父线程连验收标准都写不出来，说不出怎样算做完。complex：最大未知没有边界，任务本身又跨多个系统：根因连出在哪个系统都不知道；要在父 agent 尚未裁决的多个可行方案之间做跨系统的设计或架构取舍；父 agent 自己解决不了、要请专家咨询（Oracle）或裁决互相矛盾的结论（Judge）。检验无边界：父 agent 说不出最大未知落在哪个系统或哪条链路，也列不出候选方案；能说出其一就有边界，不归complex。跨多个系统只是complex的前提。
下限：只有第 2 类至少
medium，不归simple。这类任务测试通过不等于做对——并发交错、恢复路径、隔离泄漏、把部分成功写成整项通过都不会体现在测试结果里。按固定命令或清单核对、如实报告结果的验证仍是simple（编排后端里 Validator 固定simple与此一致）；要综合多份证据下“可以签字或发布”的结论，或当必审改动的唯一审查人，才至少medium。可复现、范围已圈定的缺陷定位不是这一类。 -
只有一部分属于上面的
medium三类时，把已闭合的实现、文档或固定清单验收拆出去按simple派，medium部分单独归档。
常见任务的对照：
- 调研或设计文档，要回答的问题已经圈定：
simple。 - 缺陷定位或修复：可复现、范围已圈定是
simple，根因可以还不知道；根因已定位的修复也是simple。 - 在测试环境实测、缺陷只记录，包括要自己构造场景：问题或清单已圈定是
simple。 - 构造制品、发布、部署或合并：按既定流程，或第一次跑但有备份或回滚，是
simple。 - 按固定规则扫描、比对或补登记（历史、配置、清单）：
simple。 - 审查：需求与验收条件明确的都是
simple，包括闭合改动、修复后的增量补审和跨模块状态机的深度审查。发布签字，或当必审改动的唯一审查人，是medium。 - 父线程写不出怎样算做完：
medium。 - 多个服务联动出错，没有复现也没有报错，不知道在哪一层：
complex。
What ships with it
10 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.
- agents/openai.yaml 180 B
- references/bootstrap.md 7.9 KB
- references/config.example.yaml 2.8 KB
- references/dispatch.md 19 KB
- references/task-template.md 3.0 KB
- scripts/bb-dispatch 76 KB
- scripts/check_codex_quota_fast.py 15 KB runs code
- scripts/test_check_codex_quota_fast.py 17 KB runs code
- scripts/test_concurrency.py 21 KB runs code
- scripts/test_dispatch.py 67 KB runs code
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 · -1 lines · +44 tokens per session 7f761146fe9d
- 11d ago Changed · +5 lines 627da3bd8d42
- 13d ago Changed 6473e520fa49
- 16d ago Changed 7ee4e3910f48
- 18d ago Changed · +2 lines 4308faa935cd
- 19d ago Changed · +7 lines 665896ffdc49
- 23d ago Changed · +5 lines · -6 tokens per session 40719d5268b8
- 24d ago Changed · +13 lines · +20 tokens per session b774c6693ba5
- 26d ago Changed e74451ff2466
- 29d ago First seen · 88 lines · 56 tokens per session scan A eae86babbb3c
bb-model-routing is a skill published in the GitHub repository hxy91819/mason-skills (3 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 5,805 once invoked, about $0.0005 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 2026-09-08.
bb-model-routing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bb-model-routinghxy91819/mason-skills | Skill | 3 | today | MIT | A | 114 | Codex |
| orbit-notionnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 112k | today | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | 2d ago | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | today | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 11d ago | MIT | A | 52 | Claude Code, Codex |