agenticforge-context

Name: agenticforge-context
Availability: InStock
Author: LittleBlacky

Construct token-aware context with configurable budgets for AgenticFORGE conversations.

75|4|Updated Mar 3, 2026

Search Tags:#context #llm #build #history #budget #prompting #token

Ready to run

npx skills add https://github.com/LittleBlacky/AgenticFORGE --skill agenticforge-context

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agenticforge-context
Source: https://github.com/LittleBlacky/AgenticFORGE/tree/main/skills/agenticforge-context
Command: npx skills add https://github.com/LittleBlacky/AgenticFORGE --skill agenticforge-context

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manage LLM token budgets by constructing token-aware context for AgenticFORGE conversations, preventing context overflow and ensuring messages fit within a model window.

Core Features & Use Cases

Configurable token budgets (maxTokens, systemTokenBudget, historyTokenBudget) to tailor context size per model.
Efficient context assembly that combines system instructions, conversation history, and user queries while respecting token limits.
Optional augmentation with retrieved or computed context (RAG-like) to improve relevance without exceeding budget.

Quick Start

Create a token-aware context for a user query using a maxTokens budget.

Frequently Asked Questions about agenticforge-context

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I manage LLM token budgets to prevent context window overflow?▼

You manage LLM token budgets by configuring maxTokens, systemTokenBudget, and historyTokenBudget to construct context that fits within model limits. This approach tracks totalTokens during assembly and indicates whether history truncation occurred to prevent overflow.

What is token-aware context building for LLM conversations?▼

Token-aware context building assembles system instructions, conversation history, and user queries while respecting configurable token limits. It tracks totalTokens during assembly and flags whether truncation occurred to prevent exceeding the model window.

Can I configure separate token budgets for system prompts and conversation history?▼

Yes, you can configure separate token budgets for system prompts and conversation history. The context builder accepts configurable maxTokens, systemTokenBudget, and historyTokenBudget parameters, allowing you to tailor context size per model and agent workflow.

How do I fit long conversation history into a model's context limits without losing the user query?▼

You fit long conversation history into model limits by allocating a specific historyTokenBudget during context assembly. The builder tracks totalTokens, truncates history when necessary to prioritize the user query, and indicates when truncation occurred.

Does this context builder support adding retrieved context without exceeding the token budget?▼

Yes, the context builder supports optional augmentation with retrieved or computed context similar to RAG. It integrates external context into assembled messages while strictly respecting configured token budgets to improve relevance without overflow.

Why does my agent workflow lose track of earlier messages during long conversations?▼

Your agent workflow loses earlier messages because token-aware context assembly applies history truncation when conversation exceeds the historyTokenBudget. The builder indicates whether truncation occurred to maintain compliance with the model's maxTokens limit.