A foundational verification system that ensures file integrity and detects data drift before an AI agent performs operations.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install context-verifier
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 context-verifier 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 context-verifier?
context-verifier is an essential utility within the Openclaw Skills ecosystem designed to solve the stale data problem in AI-driven development. By computing local SHA256 hashes and verifying them before and after file operations, it ensures that the file your agent is reading is exactly the one it intends to edit. This skill consolidates hash computation, integrity verification, and severity tagging into a single agentic workflow, providing a robust layer of trust for automated coding tasks.
As a foundational component, it provides the verification infrastructure that higher-level agents depend on to maintain state consistency. By utilizing standard SHA256 algorithms locally, it maintains a high security posture, ensuring that file contents are processed on your machine rather than being transmitted to external APIs.
context-verifier Use Cases
- Verifying file integrity before an AI agent begins a complex refactoring task to ensure no background changes occurred.
- Generating context packets that bundle file metadata and checksums for audit trails or multi-agent handoffs.
- Tagging sensitive files like .env or credentials with critical severity to block unauthorized or accidental AI modifications.
- Detecting drift between a cached file version and the current filesystem state during long-running agent sessions.
How context-verifier Works
- The user or agent invokes the hash command to generate a unique SHA256 signature for a specific file or set of files.
- Severity levels are automatically assigned to files based on configurable patterns to determine the risk of modifications.
- Before performing a write operation, the agent runs a verification check to compare the current file hash against the initial signature.
- If a mismatch is detected, the skill alerts the user and suggests re-reading the file to prevent data corruption from stale context.
- For complex workflows, the packet command aggregates file metadata into a structured JSON file stored locally in the workspace.
context-verifier Setup
To get started with this part of Openclaw Skills, install it via the CLI:
openclaw install leegitw/context-verifier
Configuration is handled through .openclaw/context-verifier.yaml where you can define critical file patterns and severity rules.
context-verifier Data Schema & Taxonomy
The skill organizes data within the local workspace to ensure privacy and auditability. It uses the following structure:
| Path | Description |
|---|---|
.openclaw/context-verifier.yaml |
Primary configuration for severity patterns and rules. |
output/context-packets/ |
Directory containing JSON-formatted verification packets. |
PKT-YYYYMMDD-XXX.json |
Individual context packets containing file paths, hashes, and timestamps. |
Each packet follows a structured JSON schema including a unique ID, creation timestamp, and an array of file objects containing paths, hashes, severity levels, file sizes, and modification dates.
context-verifier Advanced Features
- Automated severity classification for critical, important, and minor files based on configurable glob patterns.
- Batch processing of files using complex glob syntax for large-scale project integrity snapshots.
- Foundational integration support for other Openclaw Skills such as failure-memory and constraint-engine.
- Secure, local-only SHA256 hash computation ensuring no file content is ever transmitted to external LLM providers.
- Support for the include-content flag to create full snapshots for documentation or non-sensitive file backups.
SKILL.md
Loading
Related Openclaw Skills
Code Patent Validator
An expert utility that converts technical code analysis findings into structured search strategies and evidence maps for intellectual property research.
Code Patent Scanner
A specialized technical analysis tool that scans repositories to identify, score, and document distinctive code patterns for intellectual property preparation.
DMM Ranking Lite
A lightweight browser automation tool for Openclaw Skills to extract and translate DMM/FANZA public rankings without needing API credentials.
Feishu Interactive Cards
A sophisticated toolset for sending and managing interactive UI elements like buttons, polls, and forms within Feishu (Lark) messages.
Ethics Guardrails
A public API-backed framework for declaring and publishing an AI agent's ethical boundaries and priority hierarchies.
failure-memory
failure-memory is a specialized system for Openclaw Skills that enables AI agents to detect, record, and learn from their own failures to prevent future recurrences.
METADATA
Featured*
