Agent skill · Workflow & Productivity

agentsop-cost-tiered-models

Split a multi-call LM workflow by cognitive load, not by accuracy: let one strong model make the few reasoning decisions and a cheap model do the many mechanical executions (Aider architect+editor, DSPy optimizer-LM vs task-LM, vLLM speculative draft+target, LangGraph supervisor+worker are the same shape). Use when designing or cost-optimizing a pipeline that calls an LM many times, when deciding which steps need a strong reasoner vs a cheap executor, or when adding an escalation valve for when the cheap tier degrades. Search keywords: reduce LLM cost, cheaper model, lower token cost, model ca

agentsopegithub.com/agentsopeGitHub ↗
claude-codeMIT
Install
npx skills add agentsope/SkillAlchemy --skill agentsop-cost-tiered-models --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 4
SKILL.md size: 12 KB
Bundled scripts: none
Version: 0.1.0
Path: skills/agentsop-cost-tiered-models/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 255
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Cost-aware Model/Role Split — "强推理者 + 廉价执行者" > 一句话:一条多次调用 LM 的工作流里,**少数调用需要推理,多数调用是机械执行**。让一个强模型做决策,让一个便宜模型干活——按认知负荷拆分,不是按"哪个更准"拆分。 > **统一声明**:Phase B 发现这个模式在 4 个 SOP 里以 4 个名字反复出现——DSPy 的 optimizer-LM vs task-LM、Aider 的 architect+editor、vLLM 的 speculative draft+target、LangGraph 的 supervisor+worker。它们是**同一个形状**。本技能把这个形状抽出来,命名为 cost-tiered models。详见 §7 跨框架对照。 --- ## 1. 何时激活 (When to activate) 任一情形成立时激活本技能: - 工作流会**对 LM 发起多次调用**,且这些调用**认知负荷不均**——有的需要规划/推理/判断,有的只是改写、抽取、格式化、应用一个已定好的决定。 - 你正在为一条 LM 流水线**选模型**,并且默认想"全程用同一个最强模型"——这是本技能要挑战的反射。 - 你有一个**强 reasoner 但执行差**的模型(典型:o1/o3 推理强但编辑代码格式脏),需要给它配一个干净的执行者。 - 你在**成本/延迟压力**下,想知道哪些调用可以降级到便宜模型而不掉质量。 - 你在设计 **agent 编排**(supervisor 路由 + worker 执行),或 **推理加速**(speculative draft + target verify),意识到这和上面是同一个决策。 **不应激活**(见 §6): - 单次调用、无内部步骤的工作流——没有可拆分的角色。 - 微型工作流(2–3 次调用、总成本可忽略)——拆分的协调开销 > 节省。 - 质量是唯一目标、成本无关紧要的场景——直接全程用最强模型。 --- ## 2. 核心心智模型 (Core Mental Model) **按认知负荷拆分:一个强模型做决策,一个便宜模型执行——而且绝大多数调用是执行。** ### 2.1 两层,不是一层 绝大多数团队的默认是"全程一个模型"。这把两种本质不同的工作混在了一个价位上: | 层 | 工作性质 | 调用频率 | 模型要求 | 选谁 | |---|---|---|---|---| | **Tier-S(决策层)** | 规划、推理、路由、判断、提案 | **少**(每任务 1–N 次) | 推理强;执行干不干净不重要 | 最强 reasoner | | **Tier-E(执行层)** | 改写、抽取、格式化、应用决定、生成草稿 | **多**(占总调

What's inside
Steps it walks through
  1. 1. 何时激活 (When to activate)
  2. 2. 核心心智模型 (Core Mental Model)
  3. 2.1 两层,不是一层
  4. 2.2 为什么"强 reasoner 执行差"是常态而非例外
  5. 2.3 三种省钱方向,同一个形状
  6. 2.4 升级阀门(escalation valve)
  7. 3. SOP 工作流 (SOP Workflow)
  8. 4. 操作模型 (Operation Model)
  9. OP-1: Role-tier mapping(角色→层映射)
  10. OP-2: The architect+editor recipe(架构师+编辑者配方)
  11. OP-3: Fallback-escalation(回退-升级阀门)
  12. OP-4: Format-by-tier(按层选输出格式)
  13. OP-5: Cheap-optimizer / expensive-task(廉价优化器 + 昂贵任务模型)
  14. OP-6: Distill-after-split(拆分后蒸馏)
Ships with 3 files
  • README.md
  • intermediate/operation_candidates.json
  • references/R1-source-evidence.md
More from SkillAlchemy
All skills →
About this skill
What does the agentsop-cost-tiered-models skill do?

Split a multi-call LM workflow by cognitive load, not by accuracy: let one strong model make the few reasoning decisions and a cheap model do the many mechanical executions (Aider architect+editor, DSPy optimizer-LM vs task-LM, vLLM speculative draft+target, LangGraph supervisor+worker are the same shape). Use when designing or cost-optimizing a pipeline that calls an LM many times, when deciding which steps need a strong reasoner vs a cheap executor, or when adding an escalation valve for when the cheap tier degrades. Search keywords: reduce LLM cost, cheaper model, lower token cost, model ca

How do I install it?

Run `npx skills add agentsope/SkillAlchemy --skill agentsop-cost-tiered-models --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From agentsope/SkillAlchemy, a repository with 255 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going