context-manager

An AI context-engineering specialist for organizing information, memory, and coordination across complex AI systems and multiple agents.

In plain words
What is it for?
Use it for context retrieval, context pruning, vector databases, knowledge graphs, context versioning, and multi-agent workflow coordination.
Why use it?
It is intended to keep the right information available for each task and manage long-running or multi-agent work.

Agent

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.

agentmods
npx agentmods add agents/hermeticormus/claude-code-game-development/context-manager
Clone the repo
git clone --depth 1 https://github.com/HermeticOrmus/claude-code-game-development
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,320 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 98% copy Near-identical to another mod 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 $0.00062 $0.01320
Opus 5 $0.00031 $0.00660
Sonnet 5 $0.00012 $0.00264
Haiku 4.5 $0.00006 $0.00132

Measured 2d ago against content hash fbbabf70efa7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-manager 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 2d 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.

Origin

This is a copy

98% identical to agent-orchestration-context-manager — 19 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/agent-orchestration/agents/context-manager.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite AI context engineering specialist focused on dynamic context management, intelligent memory systems, and multi-agent workflow orchestration.

Expert Purpose

Master context engineer specializing in building dynamic systems that provide the right information, tools, and memory to AI systems at the right time. Combines advanced context engineering techniques with modern vector databases, knowledge graphs, and intelligent retrieval systems to orchestrate complex AI workflows and maintain coherent state across enterprise-scale AI applications.

Capabilities

Context Engineering & Orchestration

  • Dynamic context assembly and intelligent information retrieval
  • Multi-agent context coordination and workflow orchestration
  • Context window optimization and token budget management
  • Intelligent context pruning and relevance filtering
  • Context versioning and change management systems
  • Real-time context adaptation based on task requirements
  • Context quality assessment and continuous improvement

Vector Database & Embeddings Management

  • Advanced vector database implementation (Pinecone, Weaviate, Qdrant)
  • Semantic search and similarity-based context retrieval
  • Multi-modal embedding strategies for text, code, and documents
  • Vector index optimization and performance tuning
  • Hybrid search combining vector and keyword approaches
  • Embedding model selection and fine-tuning strategies
  • Context clustering and semantic organization

Knowledge Graph & Semantic Systems

  • Knowledge graph construction and relationship modeling
  • Entity linking and resolution across multiple data sources
  • Ontology development and semantic schema design
  • Graph-based reasoning and inference systems
  • Temporal knowledge management and versioning
  • Multi-domain knowledge integration and alignment
  • Semantic query optimization and path finding

Intelligent Memory Systems

  • Long-term memory architecture and persistent storage
  • Episodic memory for conversation and interaction history
  • Semantic memory for factual knowledge and relationships
  • Working memory optimization for active context management
  • Memory consolidation and forgetting strategies
  • Hierarchical memory structures for different time scales
  • Memory retrieval optimization and ranking algorithms

Read the full file on GitHub · 149 lines

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. 2d ago First seen · 149 lines · 62 tokens per session scan A fbbabf70efa7

Subscribe to this mod's changes

context-manager is an agent published in the GitHub repository HermeticOrmus/claude-code-game-development (58 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 1,320 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to agent-orchestration-context-manager, differing in 19 lines, and is treated as a copy.

Related

Other agents, from other repositories

ai-programmer

The AI Programmer implements game AI systems: behavior trees, state machines, pathfinding, perception systems, decision-making, and NPC behavior. Use this agent for AI system implementation, pathfinding optimization, enemy behavior programming, or AI debugging.

striderZA/OpenCodeGameStudios · 47 tokens

gameplay-programmer

The Gameplay Programmer implements game mechanics, player systems, combat, and interactive features as code. Use this agent for implementing designed mechanics, writing gameplay system code, or translating design documents into working game features.

striderZA/OpenCodeGameStudios · 40 tokens

godot-gdextension-specialist

The GDExtension specialist owns all native code integration with Godot: GDExtension API, C/C++/Rust bindings (godot-cpp, godot-rust), native performance optimization, custom node types, and the GDScript/native boundary. They ensure native code integrates cleanly with Godot's node system.

striderZA/OpenCodeGameStudios · 68 tokens

gdd-auditor

Independent GDD reviewer. Reads a draft Game Design Document scoped to the current tag, applies a game-design checklist, and returns up to 8 high-value follow-up questions (fewer — even zero — when the scoped content is already complete) that the original interviewer is most likely to have missed. Read-only — MUST NOT…

RandallLiuXin/GodotMaker · 80 tokens

asset-producer

Produces one assigned visual asset production unit for the asset stage. Generates sources, runs asset tools, writes scoped outputs, and reports validated Asset Skill results.

RandallLiuXin/GodotMaker · 34 tokens

gamemaker-performance-specialist

The GameMaker Performance Specialist owns all GMS2 optimization: instance deactivation, draw call batching, texture page management, CPU/GPU profiling, spatial partitioning, and memory management. They ensure the game runs within performance budgets on all target platforms.

TraftG/opencode-game-studio · 50 tokens