THE CLAWSOLATOR PRINCIPLEA prompt is not a permission system.Meet the independent daemonOperator authority belongs outside the agent.
Agent Atlas / Specialist office

Scheduler agent.

Appointments, calendars and follow-ups. One clear mission; explicit tools, scoped data and operator governance.

Illustrative portrait

What this office does

Clawsolator's Atlas depicts an agent assigned to a narrowly defined workflow, not a privileged host account. Its requests can be reviewed against operator policy.

Alternative illustrative portrait

Where it belongs

Part of the Family example, operating within its assigned domain rather than assuming it can read all personal, corporate or client information.

The independent control path

Agents request. The daemon decides.

Authority is a system property—not something an agent earns by writing convincing prose.

Full architecture ↗
01 / requestScoped agent request

An agent asks to allocate resources, use a tool, or perform a protected operation.

02 / decideXMAN policy daemon

The daemon checks request identity, policy, current limits, and actual system state.

03 / approveOperator authorization

Routine permitted work can proceed; sensitive or privileged actions require explicit approval.

04 / enforceBounded executor

Rootless Podman executes supported actions; a separate privileged executor is a future design.

05 / verifyReadback and audit

Reconcile container state, journal the outcome, and notify the requester.

NO DIRECT ROOT AUTHORITY.Human-approved privileged execution is planned, not yet independently qualified.
Within policy → automatically granted. A bounded +32 MiB Podman resource request is enforced and read back; an outcome is recorded.Interactive illustration based on one reported integration test; this page performs no system operations.
AGENT ATLAS / EXECUTIVE / FAMILY

Scheduling Agent: the job, not just the avatar.

An illustrative office design for a specialized agent. A role card is not proof of a deployed integration: tools, credentials, boundaries and verification must be configured and tested.

AUTHORIZED INPUT

What it receives

Authorized calendars, time zones and meeting constraints.

REVIEWABLE OUTPUT

What it produces

Proposed schedule and notification plan.

APPROVAL BOUNDARY

What it cannot self-authorize

External invitations and major changes require authorization.

Authority comes from policies, mounts, accounts and the independent manager—not a character description or a prompt. Read the XMAN approval model →
ROLE-SPECIFIC INPUTSSCOPED CREDENTIALSHUMAN REVIEWAUDITABLE HANDOFFS

Back to the Agent Atlas →   Explore container isolation →