| name | agent-command-center |
| description | Creates a command-center view for managing multiple AI agents and human-agent workflows, including active work, owners, state, blockers, quality signals, risk level, approvals, and next decisions. Use when a leader needs visibility across an agent-powered operating system. |
| license | MIT |
| compatibility | Agent Skills compatible clients. Optional file, terminal, web, and repository access improve agent-operations workflows. |
| metadata | {"author":"Stephen Rogan","version":"1.0.0","tier":"tier-5-mega-manager","role":"Manager cockpit designer","cadence":"weekly or continuous operations"} |
Agent Command Center
Overview
Use this skill to support the leader as Manager cockpit designer in a mega-manager operating model. A single control surface that stops agent work from becoming invisible, duplicated, or ungoverned.
A mega manager is not a person who passively supervises more humans. It is a leader who manages a portfolio of humans, AI agents, workflows, memory, tools, evals, and approval gates. The agent expands span of control only when the operating system is legible, governed, and reviewable.
When to Use
Run this skill when:
- Leader has multiple agents/workflows running
- Agent work is hard to track or approve
- There are duplicate, stale, or risky automated loops
Do not use this skill to bypass judgment, accountability, security, privacy, HR, legal, customer approval, or executive decision rights.
Inputs
Gather:
- Agent/workflow inventory
- Current tasks, outputs, schedules, and owners
- Approval queues, errors, and quality signals
- Business priorities and risk classes
If key inputs are missing, label assumptions and confidence. Do not invent tools, access, facts, policies, or authority.
Workflow
Follow this sequence:
- Inventory every active agent/workflow and its owner
- Classify state: running, blocked, pending approval, stale, failed, or complete
- Surface highest-risk and highest-leverage items first
- Identify duplicates, orphaned work, and missing review loops
- Produce a weekly command-center brief and decision queue
Always finish by making the control loop visible: owner, current state, review point, approval boundary, and kill/rollback rule where relevant.
Output Format
Use this structure:
# Agent Command Center
## Objective
[What system, workflow, agent, or team capability is being designed or reviewed.]
## Current State
- Humans:
- Agents/workflows:
- Tools/data:
- Risks/unknowns:
## Design or Review
[The architecture, brief, review, command center, governance plan, eval suite, or backlog.]
## Autonomy and Approval Boundaries
- Agent may:
- Agent must not:
- Human approval required for:
## Verification
- Acceptance criteria:
- Evidence required:
- Review cadence:
- Kill/rollback trigger:
Expected deliverables:
- Agent command center brief
- Workflow state table
- Risk and approval queue
- Duplicate/stale work list
- Next decision ladder
See assets/output-template.md for a reusable version.
Human Decision Boundary
The agent may prepare, structure, evaluate, monitor, and recommend. The human leader owns final decisions, accountability, and risk acceptance. The agent must not cross these boundaries:
- Do not create more automation to solve illegibility before pruning current loops
- Do not approve agent actions automatically
- Leader owns prioritisation and kill/continue decisions
Stop for explicit approval before granting access, increasing autonomy, sending external messages, making people/customer/financial/legal commitments, changing production systems, or retaining sensitive memory.
Quality Bar
A strong output for this skill:
- Makes the human-agent operating model more legible, not more magical.
- Names owner, state, authority, review cadence, and failure response.
- Uses evidence and acceptance criteria instead of vibes.
- Reduces managerial drag without eroding accountability.
- Includes safety boundaries appropriate to autonomy level and data sensitivity.
- Creates reusable artifacts a leader can run repeatedly.
Failure Modes
Watch for these mistakes:
- Treating agents as employees with intent instead of systems with failure modes.
- Scaling autonomy before evals, logging, approval gates, and rollback exist.
- Creating invisible work that nobody owns or reviews.
- Confusing polished output with verified output.
- Adding more agents when the real problem is unclear workflow ownership.
References
- Operational control-plane patterns
- Closed-loop operator principles: visible state, owners, verification, kill rules
- Agent Skills progressive disclosure and eval loops
For the shared methodology spine, see ../../docs/SOURCE-SPINE.md.
