A specialized utility to diagnose and expand the conversation context limits of AI agents up to 1 million tokens.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-context-upgrade
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install openclaw-context-upgrade using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is OpenClaw Context Upgrade?
This skill provides a systematic approach to upgrading the context window of AI sessions, specifically targeting the transition from standard limits to ultra-high 1M token contexts. It empowers users to leverage the full power of models like GPT-5.4 by managing configuration patches and session lifecycles within the Openclaw Skills ecosystem. By ensuring proper model selection and configuration alignment, this skill eliminates common bottlenecks that prevent agents from accessing larger memory banks and ensures that the model is utilized to its full potential.
OpenClaw Context Upgrade Use Cases
- Moving a chat session from standard 272k to 1M context tokens.
- Updating global agents.defaults.contextTokens for all future AI sessions.
- Verifying current context status and diagnosing why limits haven't updated.
- Ensuring model pinning to high-context aliases like GPT-5.4 during complex workflows.
How OpenClaw Context Upgrade Works
- Performs a current state analysis using session_status to record the active model and context budget.
- Inspects the exact configuration path using gateway tools to look up existing schema values for contextTokens.
- Aligns the session with a high-context model, preferably using the GPT-5.4 alias.
- Applies a configuration patch to raise the default context budget to 1,000,000 tokens.
- Triggers an automated system restart to commit the new settings.
- Instructs the user to start a fresh chat session using reset commands to initialize the new budget.
- Conducts a final verification to confirm the context is successfully recognized as 1.0m.
OpenClaw Context Upgrade Setup
To initialize the context upgrade within the Openclaw Skills framework, you do not need to manually edit files. The agent handles the gateway patch internally. Ensure you have access to a provider supporting high-context windows.
# The agent executes the following logic internally:
# 1. gateway config.schema.lookup agents.defaults.contextTokens
# 2. gateway config.patch agents.defaults.contextTokens=1000000
After the patch is applied, remember to use the /new command in your interface to start a session with the upgraded 1M context.
OpenClaw Context Upgrade Data Schema & Taxonomy
The skill manages specific configuration keys and session metadata to ensure persistent high-context availability within Openclaw Skills:
| Configuration Key | Purpose | Expected Value |
|---|---|---|
| agents.defaults.contextTokens | Defines the default token budget for new sessions | 1000000 |
| agents.defaults.model | Sets the default model alias for the agent | GPT-5.4 |
| session_status.context | Metadata field verifying the active session limit | 1.0m |
| gateway.config.patch | Tool used to apply persistent changes | JSON Patch |
OpenClaw Context Upgrade Advanced Features
- Intelligent diagnostics to detect if provider-side caps are overriding requested Openclaw Skills limits.
- Automated configuration patching that includes session restart triggers.
- Context budget verification that distinguishes between old session reuse and fresh session initialization.
- Support for model-specific overrides to prevent fallback to lower-context LLMs.
SKILL.md
Loading
Related Openclaw Skills
kkclaw
A sophisticated desktop visualization layer and maintenance toolkit designed to give your AI agent a physical presence with emotional and voice feedback.
Substreams Search
A comprehensive toolset for discovering, visualizing, and configuring Substreams packages from the substreams.dev registry.
Membox Cloud Sync
A private, zero-knowledge encrypted sync and recovery skill for maintaining AI agent memory across multiple devices.
FastOCR
A high-performance, offline OCR tool for structured data extraction from invoices, travel tickets, and medical receipts.
Git Workflows Pro
An expert-level git management skill designed to handle complex history surgery, repository architecture, and emergency recovery with a safety-first philosophy.
Search Bot
A high-performance real-time web search skill that delivers ranked results and AI-generated summaries for up-to-date information retrieval.
Featured*
