A specialized skill that ensures AI agents maintain project continuity in Telegram by injecting context from local status files after session resets.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install session-context-injector
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-context-injector 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 Context Injector?
The Session Context Injector is a high-utility component of Openclaw Skills designed to solve the blank-slate problem encountered during AI agent interactions. When an AI session is cleared or a new collaborator joins a room, the agent typically loses its immediate project awareness. This skill bridges that gap by parsing local STATUS.md files—containing resume points, blockers, and next actions—and automatically broadcasting a structured update to the relevant Telegram chat.
By ensuring every reset is followed by a project-specific reorientation, it allows developers and teams to pick up exactly where they left off without manually re-explaining the current state. It supports multiple message formats including project room refreshes, direct message summaries for lead developers, and welcome messages for new project rooms, making it a cornerstone for professional Openclaw Skills implementations.
Session Context Injector Use Cases
- Automatically re-orienting a group chat after a scheduled session refresh.
- Onboarding new collaborators into a project room with a summary of current progress and allowed topics.
- Sending a daily activity summary to a project lead via direct message after a context clear.
- Initializing a new project room with specific context and purpose definitions to guide the AI agent.
How Session Context Injector Works
- Parse the local STATUS.md file within the project directory to extract key metadata like resume points and current blockers.
- Select the appropriate message template based on the chat type, whether it is a group, direct message, or a new room setup.
- Construct a formatted HTML message, ensuring it stays within the Telegram 4096-character limit through intelligent truncation.
- Send the context injection via the Telegram Bot API using a secure bot token retrieved from environment variables or secret management.
- Log the success or failure of the injection to the local memory files to maintain an audit trail of the Openclaw Skills activity.
Session Context Injector Setup
To integrate this into your Openclaw Skills workflow, ensure your environment is configured correctly:
# Ensure the Telegram Bot Token is available in your environment
export TELEGRAM_BOT_TOKEN="your_token_here"
# Or retrieve via 1Password if your project uses secret injection
op read "op://OpenClaw/Telegram Bot Token/credential"
# Ensure python3 is installed as the skill uses it for parsing and API calls
python3 --version
Session Context Injector Data Schema & Taxonomy
The skill interacts with the following data points to maintain project state across the Openclaw Skills ecosystem:
| Attribute | Description | Source |
|---|---|---|
| chat_id | The unique Telegram identifier for the room or user | sessions.json |
| slug | The project-specific directory name used for lookups | telegram-groups.json |
| STATUS.md | Markdown file containing RESUME FROM HERE and Blockers | projects/slug/STATUS.md |
| memory/log.md | Daily log where injection events and status codes are appended | Local filesystem |
It organizes the message output using HTML tags for robust compatibility across different Telegram clients.
Session Context Injector Advanced Features
- Smart regex-based parsing that extracts specific Markdown headings even from complex status files.
- Automated message truncation that prioritizes key project info to prevent Telegram API errors for long reports.
- Multi-variant messaging logic supporting specific templates for Group, Direct, and Welcome chat types.
- Built-in dry-run mode for developers to test injection templates in the CLI without sending live messages.
- Error-resilient workflow that logs failures to memory without breaking the primary automation loop.
SKILL.md
Loading
Related Openclaw Skills
Tool Result Size Controller
An optimization utility for AI agents that prevents context window overflow by automatically offloading large tool outputs to disk storage.
Neural Learning Engine
A lightweight AI module that simulates a neural network learning loop to enable pattern recognition and adaptive responses in intelligent agents.
Safe File Editor
A robust file editing utility for AI agents that implements atomic operations, mandatory diff previews, and automated rollback recovery.
DeFi Skills
A stateless engine that converts natural language DeFi intents into deterministic, unsigned Ethereum transactions across major protocols.
Agent Concurrency Controller
A Fail-Closed scheduling layer for Openclaw Skills designed to manage agent concurrency, prevent network conflicts, and enforce granular permission auditing.
Context Cache Manager
A sophisticated context management tool for Openclaw Skills that ensures fork-safe state inheritance and prevents token explosion through intelligent compression.
Featured*
