Model Serving
ancoleman/ai-design-components
LLM and ML model deployment for inference. An agent skill from ancoleman/ai-design-components.
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…
$ npx skills add agentsope/SkillAlchemy --skill agentsop-cost-tiered-models -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install agentsope/SkillAlchemy agentsop-cost-tiered-models --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/agentsope/SkillAlchemy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agentsop-cost-tiered-models .claude/skills/agentsop-cost-tiered-models && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "agentsop-cost-tiered-models" agent skill from https://github.com/agentsope/SkillAlchemy/tree/master/skills/agentsop-cost-tiered-models into .claude/skills/agentsop-cost-tiered-models/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentsop-cost-tiered-models", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/agentsope/SkillAlchemy/tree/master/skills/agentsop-cost-tiered-modelsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add agentsope/SkillAlchemy --skill agentsop-cost-tiered-models -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install agentsope/SkillAlchemy agentsop-cost-tiered-models --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentsope/SkillAlchemy.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/agentsop-cost-tiered-models .agents/skills/agentsop-cost-tiered-models && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agentsop-cost-tiered-models" agent skill from https://github.com/agentsope/SkillAlchemy/tree/master/skills/agentsop-cost-tiered-models into .agents/skills/agentsop-cost-tiered-models/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentsop-cost-tiered-models", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agentsope/SkillAlchemy --skill agentsop-cost-tiered-models -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install agentsope/SkillAlchemy agentsop-cost-tiered-models --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentsope/SkillAlchemy.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/agentsop-cost-tiered-models .cursor/skills/agentsop-cost-tiered-models && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agentsop-cost-tiered-models" agent skill from https://github.com/agentsope/SkillAlchemy/tree/master/skills/agentsop-cost-tiered-models into .cursor/skills/agentsop-cost-tiered-models/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentsop-cost-tiered-models", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/agentsope/SkillAlchemy.git --path skills/agentsop-cost-tiered-models--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add agentsope/SkillAlchemy --skill agentsop-cost-tiered-models -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install agentsope/SkillAlchemy agentsop-cost-tiered-models --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentsope/SkillAlchemy.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/agentsop-cost-tiered-models .gemini/skills/agentsop-cost-tiered-models && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agentsop-cost-tiered-models" agent skill from https://github.com/agentsope/SkillAlchemy/tree/master/skills/agentsop-cost-tiered-models into .gemini/skills/agentsop-cost-tiered-models/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentsop-cost-tiered-models", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install agentsope/SkillAlchemy agentsop-cost-tiered-modelsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add agentsope/SkillAlchemy --skill agentsop-cost-tiered-models -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/agentsope/SkillAlchemy.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/agentsop-cost-tiered-models .github/skills/agentsop-cost-tiered-models && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agentsop-cost-tiered-models" agent skill from https://github.com/agentsope/SkillAlchemy/tree/master/skills/agentsop-cost-tiered-models into .github/skills/agentsop-cost-tiered-models/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentsop-cost-tiered-models", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agentsope/SkillAlchemy --skill agentsop-cost-tiered-models -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install agentsope/SkillAlchemy agentsop-cost-tiered-models --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentsope/SkillAlchemy.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/agentsop-cost-tiered-models .opencode/skills/agentsop-cost-tiered-models && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agentsop-cost-tiered-models" agent skill from https://github.com/agentsope/SkillAlchemy/tree/master/skills/agentsop-cost-tiered-models into .opencode/skills/agentsop-cost-tiered-models/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentsop-cost-tiered-models", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
agentsop-cost-tiered-modelsSplit 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…
Agentsop Cost Tiered Models is an agent skill from agentsope/SkillAlchemy. 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…
Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `README.md`, `intermediate/operation_candidates.json` and `references/R1-source-evidence.md`).
It sits in AI & LLM Engineering, covering LLM cost and token optimization, LLM inference and serving and Building AI agents. It works with vLLM and LangGraph. The repository describes itself as: From thought to skill. From signal to structure. The licence is MIT.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit d0f0355. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Agentsop Cost Tiered Models loads about 3k tokens when it runs, and up to ~4.6k if it reads all its reference files. Until then it costs about 178 tokens; SKILL.md has 751 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from agentsope/SkillAlchemy at commit d0f0355, republished under its MIT licence (© agentsope). 751 words, ~2,990 tokens.
.claude/skills/agentsop-cost-tiered-models/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.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。
任一情形成立时激活本技能:
不应激活(见 §6):
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。
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(占总调用 80%+) | 听话、格式干净、便宜、快 | 便宜/快模型 |
关键洞察:成本由调用次数主导,调用次数由执行层主导。所以把执行层降级到便宜模型,省下大部分成本,却几乎不碰决策质量——因为决策层调用次数少,仍然用最强模型。
推理能力和指令依从(产出干净的 diff/JSON/格式)是两种不同的能力,不总同向。Aider 的 Polyglot 数据是最干净的证据:o1-preview 单独跑 79.7%,但它当 architect 配一个便宜 editor 后,整体到 82.7%–85%——两次便宜的专门调用胜过一次又贵又全能的调用 [aider.chat/2024/09/26/architect.html]。强模型负责"想",便宜模型负责"把想法落成格式正确的编辑"。
三者都是"强决策 + 廉价执行"的拆分,只是优化目标不同。
拆分不是单向的。便宜执行者会在某些输入上失败或退化(格式错、跑题、质量塌)。正确的设计带一个回退-升级阀门:检测到执行层失败 → 把这一步升级到强模型重试。便宜执行者覆盖 80–95% 的常规输入,强模型兜底长尾。这把"省钱"和"不掉质量"同时拿到。
[Step 0] 列出工作流里所有 LM 调用
└─ 对每次调用记:它在"想"还是在"做"?预期调用频率?
[Step 1] 给每次调用打认知负荷标签
├─ 高推理(规划/路由/判断/提案/纠错) → 候选 Tier-S
└─ 机械执行(改写/抽取/格式化/应用决定/草稿) → 候选 Tier-E
规则:把"需要全局判断 / 一旦错代价高 / 频率低"的归 Tier-S,
其余尽量下沉到 Tier-E。
[Step 2] 分配模型层
├─ Tier-S → 你能负担的最强 reasoner(少量调用,单价高无所谓)
├─ Tier-E → 便宜/快模型(大量调用,单价主导总成本)
└─ 给 Tier-E 选最适配它的输出格式(弱模型用 whole/简单 schema,
不要逼它产 token 高效但易错的 diff)。
[Step 3] 度量质量 delta(必须做,否则是赌博)
├─ baseline:全程强模型的质量分 + 成本
├─ split:S+E 拆分后的质量分 + 成本
├─ 看 (质量 delta, 成本 delta) 这一对,不要只看其一
└─ 在你自己的真实任务上量,不要信别人 benchmark 的绝对数
[Step 4] 装升级阀门
├─ 定义"执行层失败"的可检测信号(格式不合法 / 测试不过 /
│ schema 校验失败 / 自评分低)
├─ 失败 → 升级到 Tier-S 重试这一步(或换执行格式重试)
└─ 记录升级率:若 >30%,说明这步本就属于 Tier-S,重新归类
[Step 5] 调拆分点(tune the split)
├─ 升级率高 / 质量掉太多 → 把更多步上移到 Tier-S
├─ 升级率近 0 / 质量持平 → 把更多步下沉到 Tier-E,再省一截
└─ 拆分点是个滑块,不是开关;按 Step 3 的数往返调editor-diff/editor-whole)。BootstrapFinetune(student=Llama-3.2-1B, teacher=gpt-4o-mini),先在大模型优化再蒸馏 [dspy SKILL §4.1]。警告:换 task-LM 家族必须重编译/重测,大模型的 verbose CoT demo 会让小模型"鹦鹉学舌长度而无推理" [dspy SKILL Case B]。触发:硬推理编码任务;你有 o1/o3(强 reasoner,但单独跑编辑脏)。开 architect 等于把每个任务从 1 次调用变 2 次,token 成本接近翻倍。
张力:
决策规则:
| 情况 | 建议 |
|---|---|
| reasoner 执行也干净(GPT-4o / Sonnet 单跑) | 不开 architect,单跑省钱省时 |
| reasoner 执行差(o1/o3 单跑格式脏) | 开 architect:强 reasoner + 便宜干净 editor → +3pp~+5pp |
| 追 SOTA、能等慢 | o1-preview + o1-mini(whole) → 85%("probably not practical for interactive use") |
| 例行/低价值编辑 | 单跑,别拆 |
可提取操作:拆分的收益 = (质量 delta) × (任务价值) − (额外调用成本)。reasoner 执行已干净时 delta≈0,不拆;reasoner 执行差时 delta 大,拆。
Evidence: [aider.chat/2024/09/26/architect.html]。
触发:Tier-E 用便宜模型干活,部分输入上质量明显塌(代码改错、抽取漏字段、格式反复非法),但多数输入仍正常。是把整层换回强模型,还是只升级失败的那部分?
张力:
决策规则:
可提取操作:升级率是拆分点是否放对的体温计。它不是要清零,而是要稳定在低位;持续高升级率 = 拆分点划错了。
Evidence: vLLM speculative——高 QPS 下 draft 被频繁拒、speculation 反而偷算力,此时该关 [docs.vllm.ai speculative_decoding],同构于"升级率太高就别拆";Aider 编辑错误升级模型/换格式 [aider.chat/troubleshooting/edit-errors]。
最常见的默认值,也是本技能要挑战的反射。它把少量高价值决策调用和大量机械执行调用按同一个价位收费——要么为执行层overpay(全用最强),要么为决策层欠配(全用便宜,难题翻车)。先按 §2.1 分层,再选模型。
2–3 次调用、总成本可忽略的工作流,拆成 S+E 两层引入的协调/翻译开销(supervisor 翻译 worker 输出要多花 token [langgraph Case 2];architect 多一次往返)经常超过节省。拆分有固定成本,只在调用次数多、执行层占大头时才回本。
凭"便宜模型应该够用"的直觉降级,不在自己任务上量 (质量 delta, 成本 delta)。别人 benchmark 的绝对数不可移植——Aider 的 85% 是 Polyglot 上特定模型对的结果,不是你的任务的保证。必须按 §3 Step 3 自测。
逼弱 editor 产 token 高效但字节敏感的 diff,或把代码包进 JSON tool-call。弱模型在这些格式上合规率塌。便宜执行者要配它擅长的格式(whole / 简单 schema),见 OP-4。
便宜执行者必然有长尾失败。没有失败检测 + 升级回退,坏输出直接进产物。拆分必须连阀门一起设计(OP-3),否则省的钱用 debug 坏结果赔回去。
"要么全强要么全便宜"是把连续的拆分点退化成二元开关。正确做法是按升级率/质量 delta 往返微调哪些步在哪层(§3 Step 5)。
把为大模型调好的拆分/提示原样套到小模型上。DSPy 明示"为 GPT-4 优化的复杂管线在 Llama-3-8B 上通常崩" [dspy Case B]。换执行层模型家族 = 重测拆分,不是免费迁移。
本技能适用当:工作流多次调用 LM;调用间认知负荷不均;成本/延迟有约束;你能在自己任务上量质量 delta。
本技能不适用当:单次调用、无内部步骤(无角色可拆);微型工作流(拆分开销 > 节省,见反模式 2);质量是唯一目标且预算无限(直接全程最强模型);本质是"选哪个推理引擎"而非"如何分层用模型"(那是 llm-engine-selection 技能)。
同一个形状,四个名字。 每一行都是"强模型决策 + 廉价模型执行 + 失败时回退/纠正"。
| 框架 | 这个模式叫什么 | Tier-S(强/决策) | Tier-E(廉价/执行) | 升级/纠正阀门 | 公开证据 |
|---|---|---|---|---|---|
| Aider | architect + editor | architect 模型(o1-preview)出自然语言方案 | editor 模型(Sonnet/o1-mini)落成 diff | 编辑错误→升级模型/换格式重试 | Polyglot 79.7%→82.7%→85% [aider.chat/2024/09/26] |
| DSPy | optimizer-LM vs task-LM | 这里是镜像:被服务的 task-LM(gpt-4o)才贵;脚手架可降级 | optimizer-LM(gpt-4o-mini)跑提示搜索/提案 | 优化平台→重编译/换 LM 家族 | mini 优化器 + 4o 任务,质量持平成本大降 [dspy #1596] |
| LangGraph | supervisor + worker | supervisor 路由/综合/决定下一步 | worker sub-agent 执行具体子任务 | supervisor 重新路由;swarm 互相 handoff | supervisor 比 swarm 多花 token(翻译开销)[langgraph Case 2] |
| vLLM | speculative draft + target | target 模型验证、给真分布 | draft 模型(小/EAGLE/n-gram)先草拟 token | 验证拒绝→用 target 分布纠正;高 QPS 关闭 | 最高 ~2.5× 解码加速 [developers.redhat.com 2025 eagle3] |
DSPy 行里便宜的是 optimizer(脚手架/meta 层),贵的是 task(最终产物)。这不矛盾——判据始终是 §2 那一条:质量直接进最终产物的调用用强模型,只是脚手架的调用降级。在 Aider/LangGraph/vLLM 里执行层是产物的一部分但机械,所以降级;在 DSPy 里 optimizer 不进产物,所以降级。同一个原则,不同的"哪类是脚手架"。
先问每次 LM 调用:它的输出是最终产物,还是脚手架/草稿/可被验证的提议? 是产物且需判断 → Tier-S。是草稿/脚手架/可验证提议 → Tier-E + 升级阀门。
© agentsope, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (references) in skills/agentsop-cost-tiered-models of agentsope/SkillAlchemy.
Open the folder on GitHubat commit d0f0355
Agentsop Cost Tiered Models next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agentsop Cost Tiered Models this skillagentsope/SkillAlchemy | 436 | — | ~3k | Automated safety check: Pass | MIT | |
| Model Servingancoleman/ai-design-components | 525 | — | ~3.4k | Automated safety check: Pass | MIT | |
| Prefix Cache Replaybenchflow-ai/skillsbench | 1.8k | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Mem0 Platform SDKmem0ai/mem0 | 67k | 1 repos | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| SageMaker Serving Image Selectionhuggingface/skills | 11k | 1 repos | ~4.6k | Automated safety check: Pass | Apache-2.0 | |
| Aider DelegateamElnagdy/delegate-skills | 2.3k | 2 repos | ~3k | Automated safety check: Pass | MIT |
ancoleman/ai-design-components
LLM and ML model deployment for inference. An agent skill from ancoleman/ai-design-components.
benchflow-ai/skillsbench
Replay an LLM inference request trace (Mooncake / vLLM / SGLang hashids format) against a block-level KV prefix cache and compute hit statistics.
mem0ai/mem0
Adds persistent memory to AI apps with the Mem0 Python and TypeScript SDKs: store, search, update and delete user memories, with framework integrations.
huggingface/skills
Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.
amElnagdy/delegate-skills
Delegate a coding task to Aider (aider) as a background implementer, then review its diff and land it yourself.
ComposioHQ/awesome-claude-skills
Debugs LangChain and LangGraph agents by pulling recent execution traces with the langsmith-fetch CLI and reporting errors, tool calls, timings and token use.
agentsope/SkillAlchemy
SOP for terminal-based, git-native AI pair programming with Aider (git work-tree + tree-sitter repo-map + edit-format + human-in-loop REPL).
agentsope/SkillAlchemy
Coder-agent working-file budget discipline: keep the editable working set (files you /add into writable context) under ~25k tokens, separate "read" from "edit", delegate breadth to a read-only…
agentsope/SkillAlchemy
SOP for building multi-agent systems with CrewAI — role-based collaboration, sequential/hierarchical processes, Flows, memory, delegation.
agentsope/SkillAlchemy
SOP for building LLM applications on Dify — visual workflow + chatflow + agent + RAG knowledge base + plugin marketplace + observability, self-hostable.
agentsope/SkillAlchemy
Designs multiscale chunking for RAG by embedding small units for retrieval precision and returning larger context for synthesis.
agentsope/SkillAlchemy
Enhancement-overlay skill — the DECISION + WIRING layer for LM observability that the single-backend skills [[langsmith]], [[phoenix]], [[mlflow]] do NOT cover.
Categories
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…. Agentsop Cost Tiered Models is an agent skill from agentsope/SkillAlchemy. 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).
Agentsop Cost Tiered Models fits situations like: cost-optimizing a pipeline that calls an LM many times; deciding which steps need a strong reasoner vs a cheap executor; adding an escalation valve for when the cheap tier degrades.
Run `npx skills add agentsope/SkillAlchemy --skill agentsop-cost-tiered-models -a claude-code`. Or copy the skill folder (skills/agentsop-cost-tiered-models in agentsope/SkillAlchemy) into .claude/skills/agentsop-cost-tiered-models in your project. Claude Code loads it when a task matches its description.
Run `npx skills add agentsope/SkillAlchemy --skill agentsop-cost-tiered-models -a codex`. Or copy the skill folder (skills/agentsop-cost-tiered-models in agentsope/SkillAlchemy) into .agents/skills/agentsop-cost-tiered-models in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agentsope/SkillAlchemy --skill agentsop-cost-tiered-models -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agentsop-cost-tiered-models, .gemini/skills/agentsop-cost-tiered-models, .github/skills/agentsop-cost-tiered-models and .opencode/skills/agentsop-cost-tiered-models in your project.
SKILL.md names no scripts, command-line tools or credentials: Agentsop Cost Tiered Models is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Agentsop Cost Tiered Models is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Agentsop Cost Tiered Models: Model Serving (ancoleman/ai-design-components, 525 stars), Prefix Cache Replay (benchflow-ai/skillsbench, 1.8k stars), Mem0 Platform SDK (mem0ai/mem0, 67k stars) and SageMaker Serving Image Selection (huggingface/skills, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
agentsope (a GitHub user) maintains it in agentsope/SkillAlchemy, which has 436 GitHub stars. The repository holds 46 skills in this directory. The repository was last updated on October 9, 2026.
Source: agentsope/SkillAlchemy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.