cost-aware-llm-pipeline SKILL.md skillA
cost-aware-llm-pipeline from hashgraph-online/awesome-codex-plugins is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add hashgraph-online/awesome-codex-plugins/cost-aware-llm-pipeline@git:20260512.6523792Pins git:20260512.6523792 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- hashgraph-online/awesome-codex-plugins
- Path
plugins/Colin4k1024/tsp/skills/cost-aware-llm-pipeline/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260512.6523792, committed May 12, 2026
- Size
- 3,020 bytes
- Repository stars
- 1,537
- License
- Apache-2.0
成本感知 LLM 管道,根据任务复杂度选择合适模型, 管理上下文预算,避免在长会话末尾做大型重构。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Cost-Aware LLM Pipeline Skill 成本感知 LLM 管道,根据任务复杂度选择合适模型,管理上下文预算。 ## 何时激活 - 需要优化模型选择以控制成本 - 需要管理上下文使用预算 - 需要为不同复杂度任务选择合适模型 - 需要在长会话中避免上下文溢出 ## 模型选择策略 ### Haiku (轻量级) **使用场景**: - 简单任务:语法修正、格式化、小改动 - 频繁调用:grep、glob、文件探索 - 工具调用规划 **成本**: ~$0.001/1K tokens ### Sonnet (主开发) **使用场景**: - 主要开发工作 - 复杂编码任务 - 多文件重构 - 代码审查 **成本**: ~$0.01/1K tokens ### Opus (深度推理) **使用场景**: - 复杂架构决策 - 深度推理任务 - 新技术调研 - 关键问题调试 **成本**: ~$0.05/1K tokens ## 上下文预算管理 ### 预算规则 | 上下文位置 | 可用空间 | 建议 | |-----------|---------|------| | 前 20% | 宽松 | 探索、研究、讨论 | | 中间 60% | 谨慎 | 核心实现、详细代码 | | 最后 20% | 压缩 | 整理、总结、收尾 | ### 避免的错误 - ❌ 在上下文最后 10% 做大型重构 - ❌ 在低上下文空间启动复杂任务 - ❌ 用 Opus 处理 Haiku 就能完成的任务 ### 正确做法 - ✅ 在上下文中间启动复杂任务 - ✅ 在低空间使用 Haiku 做简单任务 - ✅ 定期压缩上下文避免溢出 ## 任务复杂度分级 ### L1: 简单(用 Haiku) - 语法修正 - 文件格式化 - 简单搜索替换 - README 更新 ### L2: 中等(用 Sonnet) - 函数实现 - 单元测试编写 - 代码审查 - Bug 修复 ### L3: 复杂(用 Sonnet 或 Opus) - 多文件重构 - 架构设计 - 复杂调试 - 新模块设计 ### L4: 深度(用 Opus) - ADR 编写 - 架构决策 - 性能优化 - 跨系统设计 ## 成本优化技巧 ### 1. 批处理相似任务 ```bash # 不好:多次调用,每次都加载上下文 /edit file1.ts /edit file2.ts /edit file3.ts # 好:一次调用处理多个文件 /multi-edit file1.ts file2.ts file3.ts ``` ### 2. 使用上下文压缩 ``` 长会话后运行: /compact 保留决策和结论,丢弃中间追踪 ``` ### 3. 选择正确模型 …
Read the whole file at its exact version.
How to install
mdr add hashgraph-online/awesome-codex-plugins/cost-aware-llm-pipeline@sha256:79932d01581ba2d8The line at the top of this page pins the label git:20260512.6523792, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_chjh4iuvzdhledbl)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on May 12, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3020 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
hashgraph-online/awesome-codex-plugins · 1,537 stars · license Apache-2.0 · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_chjh4iuvzdhledbl GET https://markdownregistry.com/api/v1/resolve?ref=hashgraph-online/awesome-codex-plugins/cost-aware-llm-pipeline GET https://markdownregistry.com/api/v1/blob/79932d01581ba2d8dbf5dac3dce9be5b8a995d2550d6fb0f6e14d7fc0c38a4a2
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from hashgraph-online/awesome-codex-plugins
Every file in hashgraph-online/awesome-codex-plugins