llm-offloader

llm-offloader is an agent for Claude Code from seaosinc/mcp-llm-offload. It costs 153 tokens per session (1,032 once invoked), scanned A, original, MIT.

A routing agent that sends lightweight text tasks to cheaper models, such as local language models, to save the main model’s usage budget.

In plain words
What is it for?
Delegating summaries, classification, structured extraction, translation, rewriting, draft text, commit messages, pull-request descriptions, release notes, mock data, and file-by-file mapping.
Why use it?
It keeps routine work such as summaries and rewrites from consuming the main model’s capacity, while keeping code and other accuracy-critical tasks with the main agent.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Delegating summaries, classification, structured extraction, translation, rewriting, draft text, commit messages, pull-request descriptions, release notes, mock data, and file-by-file mapping.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/seaosinc/mcp-llm-offload/llm-offloader
Install

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.

Clone the repo
git clone --depth 1 https://github.com/seaosinc/mcp-llm-offload

Made for: Claude Code.

Wrote 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.

agentmods badge for llm-offloader

README.md
[![agentmods](https://agentmods.dev/badge/agents/seaosinc/mcp-llm-offload/llm-offloader/github.svg)](https://agentmods.dev/agents/seaosinc/mcp-llm-offload/llm-offloader)
Your own site
<a href="https://agentmods.dev/agents/seaosinc/mcp-llm-offload/llm-offloader"><img src="https://agentmods.dev/badge/agents/seaosinc/mcp-llm-offload/llm-offloader/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.

agentmods 80×15 button for llm-offloader

Your own site · 80×15
<a href="https://agentmods.dev/agents/seaosinc/mcp-llm-offload/llm-offloader"><img src="https://agentmods.dev/badge/agents/seaosinc/mcp-llm-offload/llm-offloader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 153 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,032 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00153 $0.01032
Opus 5 $0.00077 $0.00516
Sonnet 5 $0.00031 $0.00206
Haiku 4.5 $0.00015 $0.00103

Measured 8d ago against content hash 7d9aa1292dd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

llm-offloader 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 8d 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.

agents/llm-offloader.md · 41 lines

What it actually says

あなたはルーティングエージェントです。仕事は、軽量タスクを安価なオフロードモデルで実行し、 メインエージェントがそれにフロンティアモデルのクォータを使わずに済むようにすることです。 作業を自分で行わず、オフロードツールに委譲して結果を返します。

運用ルール:

  • 要約 → summarize を呼ぶ。既知カテゴリへの分類 → classify を呼ぶ。テキストからの フィールド/構造化データ抽出 → extract を呼ぶ。自由形式の軽量生成(言い換え、下書き、 簡単な Q&A)→ ask を呼ぶ。
  • 翻訳 → translate を呼ぶ。文章の推敲・簡潔化 → rewrite を呼ぶ。diff からのコミット メッセージ → commit_message を呼ぶ。仕様からの擬似データ → mock_data を呼ぶ。
  • diff からの PR 説明 → pr_description を呼ぶ。git log からのリリースノート → changelog を呼ぶ。glob のファイルに 1 つの op を実行する(1 つに連結しない)→ map を呼ぶ。 1 回の呼び出しでファイルごとの結果マップが返る。
  • コード、正規表現、SQL、数学、セキュリティ判断はオフロードしないこと。入力が小さく (目安として約 200 トークン未満)かつバッチでない場合は、そのままメインエージェントへ 戻すこと — 小さな入力のオフロードはメインモデルで処理するより高くつく。
  • ユーザーのテキストはそのまま渡すこと。自分で先に要約したり再考したりしない — それでは オフロードの意味がなくなる。
  • 大きな入力(ファイル、ログ、diff、多数のファイル)は、テキストを貼り付けるのではなく path(ファイルパスまたは glob)を渡すこと。サーバーがローカルで読み込むため、送られる のはパスだけ — ここがオフロードで実際にトークンを節約できる箇所。
  • ツールが Error: で始まる文字列を返したら、そのまま報告して停止すること。明示的に指示 されない限り、メインモデルで黙ってやり直さないこと。
  • オフロードモデルの出力をそのまま返すこと。前置きは最大 1 行まで。
  • タスクが重い・曖昧・正確性が重要(コード、数学、正しさが求められるユーザー向けのもの)に 見える場合は、その旨を述べてメインエージェントへ戻すこと。推測しない。

迷ったら、まず health を実行してオフロードのエンドポイントが動いているか確認すること。

Changes

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.

  1. 8d ago First seen · 41 lines · 153 tokens per session scan A 7d9aa1292dd2

Subscribe to this mod's changes

llm-offloader is an agent published in the GitHub repository seaosinc/mcp-llm-offload (0 stars, last pushed 2mo ago), licensed MIT. It adds 153 tokens to every session and 1,032 once invoked, about $0.0008 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 2026-08-31.

Related

Other agents, from other repositories

council-advisor

Use this agent when the user is facing architectural decisions, design choices, or has been stuck debugging a problem after multiple failed attempts. This agent proactively suggests consulting the council of AI agents for diverse perspectives. Examples: Context: User is designing authentication for their application…

hex/claude-council · 422 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens

clawteam-system-architect

System architect task agent — layered abstraction, separation of concerns, evolvable design, NFR-driven, contract-first APIs, explicit trade-offs; multi-view architecture, style matrix, interface principles, ADR-style decisions; DDD, data, resilience, evolution.

deepelementlab/clawcode · 59 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens