A robust lifecycle management tool that prevents context loss by automatically persisting and restoring AI agent state across compactions and restarts.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install session-state-tracker
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 session-state-tracker 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 Session State Tracker?
The Session State Tracker is a specialized utility designed to solve the common problem of context loss in long-running AI conversations. Built specifically for the Openclaw Skills ecosystem, it acts as a persistent memory layer that records the agent's current task, status, and next steps in a local Markdown file. By using lifecycle hooks, this skill ensures that critical project information survives session compactions and gateway restarts, providing a continuous workflow for complex development tasks.
This skill is part of a growing library of Openclaw Skills focused on enhancing agent autonomy and reliability. It operates entirely locally, utilizing a schema-validated SESSION_STATE.md file within your workspace root to maintain a single source of truth. Whether you are working on a multi-day coding project or managing complex deployments, this tool keeps your agent oriented and productive without manual intervention.
Session State Tracker Use Cases
- Maintaining project context and "train of thought" during long-running development sessions.
- Automatically recovering the agent's status and goals after a system restart or gateway crash.
- Ensuring the agent remains aware of blocked tasks and next steps after session memory compaction.
- Synchronizing state between different agents working within the same workspace folder.
How Session State Tracker Works
- At the beginning of a new session, the session-start hook reads the SESSION_STATE.md file and injects a summary into the agent's initial context.
- Throughout the work process, the agent or user can update the state using the session_state_write tool to keep the record fresh.
- When Openclaw triggers a compaction event, the pre-compaction hook automatically saves the current progress to prevent data loss.
- Immediately after compaction, the post-compaction hook injects a State Anchor reminder to re-orient the agent's focus.
- The cycle continues across restarts, ensuring your Openclaw Skills always have access to the latest project roadmap.
Session State Tracker Setup
Install the skill via the hub:
clawhub install qsmtco/session-state-tracker
Alternatively, manually add the skill to your openclaw.json configuration:
"skills": {
"entries": {
"session-state-tracker": { "enabled": true }
}
}
For advanced discovery features, ensure session indexing is enabled in your agent configuration to allow the skill to synthesize state from previous transcripts.
Session State Tracker Data Schema & Taxonomy
The skill manages a SESSION_STATE.md file in the workspace root. It uses a structured YAML frontmatter for machine readability and a Markdown body for human-readable context.
| Field | Type | Description |
|---|---|---|
| project | string | The name of the current active project |
| task | string | A concise description of the current objective |
| status | string | The current workflow state (active, blocked, done, in-progress) |
| last_action | string | A summary of the most recent update or change |
| next_steps | array | A list of pending actions to be completed |
| updated | string | An ISO 8601 timestamp of the last modification |
Session State Tracker Advanced Features
- Automated state discovery: Synthesizes missing state information from recent session transcripts using memory search.
- Atomic write operations: Prevents file corruption by ensuring state updates are completed successfully before replacing the old file.
- CLI integration: Provides a session-state command-line tool for developers to inspect or manually update the agent state from the terminal.
- Zero-touch automation: Seamlessly integrates with the lifecycle of other Openclaw Skills to handle state persistence without requiring explicit agent prompts.
SKILL.md
Loading
Related Openclaw Skills
Curated Search
A domain-restricted local search engine that provides authoritative technical documentation results without web spam.
ClawShop
An API-driven skill for managing product listings and metadata on Taobao and Goofish marketplaces.
Monkeytype Tracker
A powerful typing performance monitor that integrates Monkeytype statistics and personalized improvement tips into your AI agent workflow.
Anthropic Frontend Design
A high-performance design skill for building production-grade frontend interfaces that reject generic AI patterns in favor of bold, intentional aesthetics.
Token Optimizer
A comprehensive toolkit designed to drastically reduce token usage and API expenditures through intelligent context management and task-based model routing.
tokenQrusher
tokenQrusher is a high-performance optimization system that drastically reduces AI agent token usage through intelligent context filtering and heartbeat management.
METADATA
Featured*
