cost-aware-llm-pipeline SKILL.md skillA

cost-aware-llm-pipeline from affaan-m/ecc is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add affaan-m/ecc/cost-aware-llm-pipeline@git:20260829.1c42fe7

Pins git:20260829.1c42fe7 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
affaan-m/ecc
Path
docs/ja-JP/skills/cost-aware-llm-pipeline/SKILL.md
Versions recorded
5
Latest version
git:20260829.1c42fe7, committed Aug 29, 2026
First version recorded
Aug 8, 2026
Size
7,147 bytes
Repository stars
299,696
License
MIT

LLM APIの使用量のコスト最適化パターン — タスクの複雑さによるモデルルーティング、予算追跡、リトライロジック、プロンプトキャッシング。.

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

# コスト認識LLMパイプライン

品質を維持しながらLLM APIのコストをコントロールするためのパターン。モデルルーティング、予算追跡、リトライロジック、プロンプトキャッシングを組み合わせた合成可能なパイプライン。

## 起動条件

- LLM APIを呼び出すアプリケーションの構築(Claude、GPTなど)
- 複雑さが異なるアイテムのバッチ処理
- API支出の予算内に収める必要がある場合
- 複雑なタスクの品質を犠牲にせずにコストを最適化する場合

## コアコンセプト

### 1. タスクの複雑さによるモデルルーティング

シンプルなタスクには自動的に安価なモデルを選択し、複雑なタスクのために高価なモデルを予約します。

```python
MODEL_SONNET = "claude-sonnet-5"
MODEL_HAIKU = "claude-haiku-4-5-20251001"

_SONNET_TEXT_THRESHOLD = 10_000  # 文字数
_SONNET_ITEM_THRESHOLD = 30     # アイテム数

def select_model(
    text_length: int,
    item_count: int,
    force_model: str | None = None,
) -> str:
    """タスクの複雑さに基づいてモデルを選択。"""
    if force_model is not None:
        return force_model
    if text_length >= _SONNET_TEXT_THRESHOLD or item_count >= _SONNET_ITEM_THRESHOLD:
        return MODEL_SONNET  # 複雑なタスク
    return MODEL_HAIKU  # シンプルなタスク(3〜4倍安価)
```

### 2. 不変のコスト追跡

凍結データクラスで累積支出を追跡します。各API呼び出しは新しいトラッカーを返します — 状態を変更しません。

```python
from dataclasses import dataclass

@dataclass(frozen=True, slots=True)
class CostRecord:
    model: str
    input_tokens: int
    output_tokens: int
    cost_usd: float

@dataclass(frozen=True, slots=True)
class CostTracker:
    budget_limit: float = 1.00
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add affaan-m/ecc/cost-aware-llm-pipeline@sha256:dff5c6f753c1a069

The line at the top of this page pins the label git:20260829.1c42fe7, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_42zr6maapbm2w4ry.svg)](https://markdownregistry.com/a/art_42zr6maapbm2w4ry)

8 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Aug 8, 2026 and Aug 29, 2026, about one every 5 days.

versioncommittedcommitsizeaudit
git:20260829.1c42fe7 latest2026-08-29 1c42fe7 7,147 BA view · diff
git:20260829.08024bb2026-08-29 08024bb 7,012 BA view · diff
git:20260829.558aecb2026-08-29 558aecb 7,021 BA view · diff
git:20260811.fd1b11c2026-08-11 fd1b11c 6,982 BA view · diff
git:20260808.5e6c8f92026-08-08 5e6c8f9 7,023 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7147 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

GitHub

affaan-m/ecc · 299,696 stars · license MIT · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_42zr6maapbm2w4ry
GET https://markdownregistry.com/api/v1/resolve?ref=affaan-m/ecc/cost-aware-llm-pipeline
GET https://markdownregistry.com/api/v1/blob/dff5c6f753c1a0691d1671af24013d1c22b0f21e1b1c473ae69fd1f6430ddcd0

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 affaan-m/ecc

agent-introspection-debugging SKILL.md skill
affaan-m/ecc · .agents/skills/agent-introspection-debugging/SKILL.md · Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and…
git:20260918.c752aac · audit A · 299,696 stars
agent-sort SKILL.md skill
affaan-m/ecc · .agents/skills/agent-sort/SKILL.md · Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras…
git:20260918.c752aac · audit A · 299,696 stars
api-design SKILL.md skill
affaan-m/ecc · .agents/skills/api-design/SKILL.md · REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning…
git:20260918.c752aac · audit A · 299,696 stars
article-writing SKILL.md skill
affaan-m/ecc · .agents/skills/article-writing/SKILL.md · Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice…
git:20260918.c752aac · audit A · 299,696 stars
backend-patterns SKILL.md skill
affaan-m/ecc · .agents/skills/backend-patterns/SKILL.md · Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express…
git:20260918.c752aac · audit A · 299,696 stars
benchmark-methodology SKILL.md skill
affaan-m/ecc · .agents/skills/benchmark-methodology/SKILL.md · Use after competitive-platform-analysis has produced a tiered competitor set. Scores each competitor across nine…
git:20260918.c752aac · audit A · 299,696 stars
brand-discovery SKILL.md skill
affaan-m/ecc · .agents/skills/brand-discovery/SKILL.md · Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers…
git:20260918.c752aac · audit A · 299,696 stars
brand-voice SKILL.md skill
affaan-m/ecc · .agents/skills/brand-voice/SKILL.md · Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that…
git:20260918.c752aac · audit A · 299,696 stars
bun-runtime SKILL.md skill
affaan-m/ecc · .agents/skills/bun-runtime/SKILL.md · Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel…
git:20260928.48decd0 · audit B · 299,696 stars
change-impact SKILL.md skill
affaan-m/ecc · .agents/skills/change-impact/SKILL.md · Perform evidence-backed impact analysis before changing code, data, interfaces, or governance documents, then compare…
git:20261002.4f08958 · audit A · 299,696 stars
coding-standards SKILL.md skill
affaan-m/ecc · .agents/skills/coding-standards/SKILL.md · Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed…
git:20260918.c752aac · audit A · 299,696 stars
competitive-platform-analysis SKILL.md skill
affaan-m/ecc · .agents/skills/competitive-platform-analysis/SKILL.md · Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any…
git:20260918.c752aac · audit A · 299,696 stars

Every file in affaan-m/ecc

Other files named cost-aware-llm-pipeline

cost-aware-llm-pipeline SKILL.md skill
hashgraph-online/awesome-codex-plugins · plugins/Colin4k1024/tsp/skills/cost-aware-llm-pipeline/SKILL.md · 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。
git:20260512.6523792 · audit A · 1,537 stars
cost-aware-llm-pipeline SKILL.md skill
frankxai/claude-skills-library · absorbed/harness/cost-aware-llm-pipeline/SKILL.md · Pick the smallest model that can finish the task, and record the class of work. Use when routing a search, a multi-file…
git:20261010.682b2ce · audit A · 47 stars

Browse by kind, by grade A, or by owner.