A deterministic safety gate for deployment execution that enforces governance through schema validation and persona-weighted voting.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install consensus-deployment-guard
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-deployment-guard 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-deployment-guard?
consensus-deployment-guard serves as a critical governance layer within the Openclaw Skills ecosystem, acting as the final safety gate before code or infrastructure changes are executed. It provides a deterministic framework for making ALLOW, BLOCK, or REQUIRE_REWRITE decisions based on strict policy evaluations and weighted persona voting. This ensures that every deployment request is not only technically valid but also compliant with organizational risk standards.
By integrating this skill, developers and operators can automate the validation of deployment requests against hard-block policies like failed CI tests or missing rollback artifacts. It bridges the gap between agent-driven proposals and production-ready execution by providing a clear, auditable trail of decision-making artifacts that can be replayed or reviewed at any time.
consensus-deployment-guard Use Cases
- Enforcing hard-block policies when required tests or CI checks are not passing.
- Automatically requiring a rewrite when a production rollout fails to use a mandatory canary strategy.
- Validating schema migrations to prevent incompatible database changes.
- Implementing persona-weighted voting to reach a consensus on high-risk infrastructure updates.
- Auditing deployment decisions using deterministic state artifacts for compliance reporting.
How consensus-deployment-guard Works
- The skill accepts a deployment request and validates the input against a strict JSON schema, rejecting any unknown fields.
- It evaluates the request against specific governance flags, identifying hard-block risks or policy deviations that require a rewrite.
- The system executes a deterministic voting process, either using local persona weights or aggregating votes from external agents.
- A final decision status of ALLOW, BLOCK, or REQUIRE_REWRITE is generated based on the voting outcome and policy logic.
- All decision metadata and voting results are written to the configured state directory as audit artifacts for future inspection.
consensus-deployment-guard Setup
Install the package via npm to begin using it within your Openclaw Skills workflows:
npm i consensus-deployment-guard
Configure the mandatory environment variables to define where state and audit logs should be stored:
export CONSENSUS_STATE_FILE=./state.json
export CONSENSUS_STATE_ROOT=./consensus-data
You can then run the guard against an input file using node and tsx:
node --import tsx run.js --input ./examples/input.json
consensus-deployment-guard Data Schema & Taxonomy
The skill manages its state and audit trails through a structured filesystem hierarchy defined by environment variables.
| Attribute | Description |
|---|---|
CONSENSUS_STATE_FILE |
The primary JSON file tracking the current lifecycle of deployment requests. |
CONSENSUS_STATE_ROOT |
The root directory where board-native audit artifacts and decision histories are persisted. |
Decision Output |
A JSON object containing the final status (ALLOW/BLOCK/REQUIRE_REWRITE) and associated metadata. |
The schema validation is strict, ensuring that no unauthorized or malformed data affects the governance process.
consensus-deployment-guard Advanced Features
- Deterministic persona-weighted voting for consistent, reproducible governance decisions.
- External agent mode for aggregating votes across distributed Openclaw Skills nodes.
- Idempotent retry logic to handle interrupted workflows without duplicating audit trails.
- Safety-first runtime model with no network dependencies in the core decision logic.
- Support for custom rewrite policies to guide agents in correcting invalid deployment requests.
SKILL.md
Loading
Related Openclaw Skills
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.
OpenClaw Traditional Chinese Dictionary Skill
A professional-grade skill for querying official Traditional Chinese dictionaries from Taiwan's Ministry of Education with automated version management.
consensus-guard-core
A shared deterministic policy engine providing the core primitives for vote aggregation, reputation management, and schema enforcement within the Openclaw Skills ecosystem.
Consensus Interact
A local-first engine for running multi-LLM policy-based decision workflows to ensure high-confidence outcomes in agentic systems.
METADATA
Featured*
