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 hashgraph-online/awesome-codex-plugins --skill cost-aware-llm-pipelinegit clone --depth 1 https://github.com/hashgraph-online/awesome-codex-pluginsWrote 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/hashgraph-online/awesome-codex-plugins/cost-aware-llm-pipeline)<a href="https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/cost-aware-llm-pipeline"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/cost-aware-llm-pipeline/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/hashgraph-online/awesome-codex-plugins/cost-aware-llm-pipeline"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/cost-aware-llm-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.00925 |
| Opus 5 | $0.00021 | $0.00463 |
| Sonnet 5 | $0.00008 | $0.00185 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
cost-aware-llm-pipeline 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 4d ago.
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.
What it actually 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
# 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
# 不好的做法
用 Opus 写 README
# 好的做法
用 Haiku 写 README
用 Sonnet 实现核心逻辑
用 Opus 做架构决策
与其他 Skills 的关系
| Skill | 关系 |
|---|---|
| Strategic Compact | 提供上下文压缩以保持低使用率 |
| Continuous Learning | 从成本数据中学习优化模型选择 |
| Memory Persistence | 保存会话摘要以支持上下文重建 |
命令接入
/cost-estimate <task>- 估算任务成本/model-select <complexity>- 建议模型选择/context-budget- 显示当前上下文预算
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.
- 4d ago First seen · 139 lines · 42 tokens per session scan A 79932d01581b
cost-aware-llm-pipeline is a skill published in the GitHub repository hashgraph-online/awesome-codex-plugins (968 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 925 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 2026-09-05.
Other skills, from other repositories
search
Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.
ai-wrapper-product-v2
AI Wrapper Product workflow skill. Use this skill when the user needs Expert in building products that wrap AI APIs (OpenAI, Anthropic, and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
kling-prompter
A prompt-writing guide for Kling 3.0, a video-generation model. It covers short videos, story-driven videos with dialogue or sound, and animating an existing reference image.
happyhorse-prompter
A tool for writing short prompts for HappyHorse 1.0, an AI video generator that can create video with sound. Its prompts put the main subject first, specify the camera, and describe audible sound when needed.
seedance-prompter
A prompt-writing guide for Doubao Seedance 2.0, an AI model that generates videos from written instructions.
ask-short-answer-first
Master the Bottom Line Up Front (BLUF) prompting pattern to get the direct 2-line answer immediately, eliminating preamble fluff and saving reading time.