OrgX Operations Agent

OrgX operations execution contract for OpenClaw. Use for reliability, incident response, runbooks, cost controls, and rollout safety.

Security Scan

This is a high-level operations policy/runbook contract that is internally consistent with its stated purpose, but it is high-level and leaves important details about mutation hooks and approval flow undefined.

Purpose & Capability

Name/description match the content: the SKILL.md defines an operations persona, runbook/output standards, and a reporting protocol for operations actions. It does not request unrelated binaries, credentials, or filesystem access, which is proportionate for an instruction-only operations contract.

Instruction Scope

The instructions are high-level policy rather than actionable step-by-step commands. They do not instruct the agent to read files or exfiltrate data, but they do grant broad discretion (e.g., defaulting to reversible actions, invoking mutation via 'orgx_apply_changeset' when mutation tools are available). That open-ended autonomy around state changes is expected for an ops contract but should be backed by platform-level constraints and clear approval flows.

Install Mechanism

No install spec and no code files — lowest-risk category. Nothing is downloaded or written to disk by the skill itself.

Credentials

The SKILL.md references three protocol hooks ('orgx_emit_activity', 'orgx_request_decision', 'orgx_apply_changeset') but declares no required environment variables or credentials. This is plausible if those hooks are provided by the host platform, but the skill does not document what permissions or tokens (if any) are needed to perform mutations, which should be clarified.

Persistence & Privilege

The skill does not request 'always: true' and does not modify other skills or system-wide configs. It can be invoked autonomously by default (platform default), which is reasonable for an ops agent; however, autonomous invocation plus the ability to apply changes increases potential impact and should be governed by platform safeguards.

Assessment

This skill is a policy/runbook template for operations and appears coherent. Before installing, confirm how the three protocol hooks map to your platform: what implementation provides orgx_emit_activity, orgx_request_decision, and orgx_apply_changeset, what credentials or permissions they require, and whether there are enforced human approvals and audit logs for any state-changing actions. If you plan to allow autonomous invocation, restrict or require explicit approvals for orgx_apply_changeset calls in production and test the contract in a staging environment first. If those hooks are not provided by your platform, treat this skill as incomplete and require concrete integration details before trusting it to perform or authorize changes.

OrgX Operations Agent (OpenClaw)

This skill defines how the OrgX Operations agent behaves when running inside OpenClaw.

Persona

• Voice: cautious, thorough, pragmatic.
• Autonomy: default to reversible actions; add guardrails before speed.
• Consideration: assume production is fragile unless proven otherwise; reduce on-call burden.

Primary Contract

• Prefer reversible actions and clear rollback paths.
• Treat production changes as high risk unless explicitly approved.
• Document runbooks so someone else can execute them safely.

Output Standards

For ops deliverables:

• what can go wrong
• detection signals
• mitigations/rollback
• step-by-step runbook
• verification checklist

Reporting Protocol (OrgX)

• orgx_emit_activity for progress and status.
• orgx_request_decision for blocking human decisions in default-safe mode.
• orgx_apply_changeset for state changes when the operations scope exposes mutation tools.