A shared deterministic policy engine providing the core primitives for vote aggregation, reputation management, and schema enforcement within the Openclaw Skills ecosystem.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install consensus-guard-core
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 consensus-guard-core 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 consensus-guard-core?
consensus-guard-core acts as the foundational policy infrastructure for the Consensus.Tools family of agents. It is designed to prevent logic drift across different guard types by providing a centralized library of deterministic functions. By utilizing this core package, developers can ensure that their Openclaw Skills maintain consistent decision semantics, making workflows more reliable and easier to audit.
The package provides essential tools for hard-block taxonomy, weighted vote aggregation, and reputation clamping. It is specifically built for LLM orchestration where replayable and comparable behavior across different domains is critical for maintaining the integrity of decentralized or multi-agent governance systems.
consensus-guard-core Use Cases
- Standardizing governance policies across diverse Openclaw Skills to prevent inconsistent decision logic.
- Implementing deterministic vote aggregation in multi-agent environments to ensure repeatable results.
- Managing agent reputation with strict clamping rules to prevent volatility in trust metrics.
- Ensuring idempotency in tool calls to allow for safe retries without duplicating state changes.
- Scaling artifact lookups across agent boards using standardized indexing and read helpers.
How consensus-guard-core Works
- The skill identifies the governance context by reading environment variables like CONSENSUS_STATE_ROOT.
- It applies strict schema enforcement to reject unknown fields and maintain data integrity during agent interactions.
- The aggregateVotes function processes incoming agent inputs based on a deterministic policy to reach a consensus.
- Idempotency keys are generated for every action to ensure that the execution lifecycle is retry-safe.
- Decision artifacts and reputation updates are committed to the filesystem using standardized write helpers.
consensus-guard-core Setup
To integrate these primitives into your Openclaw Skills, install the package via npm:
npm i consensus-guard-core
Configure your environment to point to your consensus state files:
export CONSENSUS_STATE_FILE=path/to/state.json
export CONSENSUS_STATE_ROOT=path/to/board/root
Run tests to verify the installation:
npm test
consensus-guard-core Data Schema & Taxonomy
| Data Component | Description | Storage Format |
|---|---|---|
| State Root | The base directory for all consensus-related artifacts | Filesystem Path |
| Artifacts | JSON records of specific decisions and board updates | .json files |
| Persona Set | Indexed collections of agent identities and current reputation | JSON Array |
| Idempotency Keys | Unique identifiers used to prevent duplicate executions | String (UUID/Hash) |
consensus-guard-core Advanced Features
- Support for the canonical invoke() entrypoint, allowing primitives-only delegation for complex agent handlers.
- Comprehensive hard-block taxonomy for strict policy enforcement across Openclaw Skills.
- Integrated board orchestration via shared consensus-interact contract wrappers.
- Built-in reputation update rules with automatic clamping to maintain system stability.
- Indexed artifact lookup optimized for scalable board read operations.
SKILL.md
Loading
Related Openclaw Skills
consensus-deployment-guard
A deterministic safety gate for deployment execution that enforces governance through schema validation and persona-weighted voting.
Consensus Code Merge Guard
A persona-weighted governance tool for AI-assisted engineering that evaluates PR risks and automates merge decisions.
Consensus Agent Action Guard
A pre-execution safety gate that uses persona-weighted consensus to govern high-risk AI agent actions before they cause irreversible side effects.
Sutrena
Deploy websites, forms, and dashboards instantly through a simple API with no build steps or hosting configuration required.
Consensus Interact
A local-first engine for running multi-LLM policy-based decision workflows to ensure high-confidence outcomes in agentic systems.
Consensus Permission Escalation Guard
A deterministic safety gate for IAM and privilege elevation requests in automated agent workflows.
METADATA
Featured*
