Arch Lens Operational

Operational Architecture Lens

Cognitive Mode: Operational Primary Question: "How is it run and monitored?" Focus: CLI Workflows, Configuration, Observability, Task Commands

When to Use

• Need to understand operator/admin perspective
• Documenting CLI commands and workflows
• Analyzing configuration and monitoring setup
• User invokes /autoskillit:arch-lens-operational or /autoskillit:make-arch-diag operational

Critical Constraints

NEVER:

• Modify any source code files
• Include internal implementation details
• Show code-level patterns
• Run subagents in the background (run_in_background: true is prohibited)

ALWAYS:

• Focus on OPERATOR experience
• Show CLI commands and their purposes
• Document configuration hierarchy
• Include monitoring and logging outputs
• BEFORE creating any diagram, LOAD the /autoskillit:mermaid skill using the Skill tool - this is MANDATORY
• If the Skill tool cannot be used (disable-model-invocation) or refuses this invocation, do NOT proceed with diagram creation. Abort this step and omit the diagram from output.
• After writing the diagram file, emit the absolute path as a structured output

token as your final output. Resolve the relative temp/arch-lens-operational/... save path to absolute by prepending the full CWD: `` diagram_path = /absolute/cwd/temp/arch-lens-operational/{filename}.md `` This token is MANDATORY — the pipeline cannot proceed without it.

Arguments

/autoskillit:arch-lens-operational [context_path]

• context_path (optional) — Absolute path to a PR context file containing new files

(★-prefixed) and modified files (●-prefixed) from the PR diff. When provided, read this file before beginning analysis and focus the diagram on the architectural areas affected by these specific files. When absent, explore the full CWD.

---

Analysis Workflow

Step 0: Read PR context (when provided)

If a context_path positional argument is present:

1. Read the file at context_path
2. Extract: new files list (★-prefixed), modified files list (●-prefixed)
3. Focus Step 1 exploration on the modules/components these files belong to
4. Apply ★ prefix on diagram nodes representing new files/components
5. Apply ● prefix on diagram nodes representing modified files/components

If no context_path is provided, skip this step and explore the full CWD in Step 1.

Step 1: Launch Parallel Exploration Subagents

Spawn Explore subagents to investigate:

CLI Entry Points

• Find all CLI commands
• Identify command groups and subcommands
• Look for: CLI frameworks (Click, argparse, Commander, etc.), entry points, main commands

Configuration

• Find configuration sources
• Identify environment variables
• Look for: config files (config.yaml, .env, settings.json, application.yml), environment variable usage, configuration libraries

Task Automation

• Find task runner definitions
• Identify automation scripts
• Look for: Taskfile.yml, Makefile, package.json scripts, Rakefile, scripts/ directory

Logging & Monitoring

• Find logging configuration
• Identify observability outputs
• Look for: logging configuration, log files, metrics, activity logs, {{AUTOSKILLIT_TEMP}}/ output directories

Status & Health

• Find status/health commands
• Identify diagnostic outputs
• Look for: status, health, info, diagnose, check commands

Reset & Recovery

• Find reset/cleanup commands
• Identify recovery operations
• Look for: reset, clean, clear, purge, restore commands

Step 2: Map Operator Workflows

Document common operator workflows:

• Create: How to start new work
• Run: How to execute
• Monitor: How to check status
• Debug: How to diagnose issues
• Reset: How to recover from errors

CRITICAL - Analyze Read/Write Direction: For EVERY operational component:

• Configuration: READ from env/files (input to system)
• State tracking: Does the system READ and WRITE, or just WRITE?
• Logs/monitoring: Typically WRITE-only (system writes, humans read)
• Status commands: READ from state to display

Clearly categorize:

• State (read/write): System reads back to make decisions
• Artifacts (write-only): System writes for human inspection, never reads back
• Config (read-only): System reads but doesn't modify

Step 3: Document Configuration Hierarchy

Example pattern (adjust to actual system):

1. Environment Variables (highest priority)
2. Secret files (e.g., .secrets.toml, .env.local)
3. Project config (e.g., config.yaml, settings.json)
4. Defaults (lowest priority)

Step 4: Create the Diagram

Use flowchart with:

Direction: TB for hierarchical command structure

Subgraphs:

• CLI Entry Points (commands)
• Configuration (sources)
• Registry/State (tracking)
• Monitoring (observability)
• Task Commands (automation)

Node Styling:

• cli class: CLI commands
• phase class: Configuration sources
• stateNode class: State tracking (database, registry)
• output class: Monitoring outputs
• handler class: Task automation commands

Show Relationships:

• Commands to configuration
• Commands to state tracking
• State to monitoring outputs

Step 5: Write Output

Write the diagram to: {{AUTOSKILLIT_TEMP}}/arch-lens-operational/arch_diag_operational_{YYYY-MM-DD_HHMMSS}.md (relative to the current working directory)

After writing the diagram file, emit a structured output line:

> IMPORTANT: Emit the structured output tokens as literal plain text with no > markdown formatting on the token names. Do not wrap token names in **bold**, > *italic*, or any other markdown. The adjudicator performs a regex match on the > exact token name — decorators cause match failure.

diagram_path = {absolute_path_to_diagram_file}

---

Output Template

# Operational Diagram: {System Name}

**Lens:** Operational (Administration)
**Question:** How is it run and monitored?
**Date:** {YYYY-MM-DD}
**Scope:** {What was analyzed}

## CLI Commands Quick Reference

| Command | Purpose | Key Flags |
|---------|---------|-----------|
| {command} | {purpose} | {flags} |

## Operational Diagram

```mermaid
%%{init: {'flowchart': {'nodeSpacing': 50, 'rankSpacing': 60, 'curve': 'basis'}}}%%
flowchart TB
    %% CLASS DEFINITIONS %%
    classDef cli fill:#1a237e,stroke:#7986cb,stroke-width:2px,color:#fff;
    classDef stateNode fill:#004d40,stroke:#4db6ac,stroke-width:2px,color:#fff;
    classDef handler fill:#e65100,stroke:#ffb74d,stroke-width:2px,color:#fff;
    classDef phase fill:#6a1b9a,stroke:#ba68c8,stroke-width:2px,color:#fff;
    classDef output fill:#00695c,stroke:#4db6ac,stroke-width:2px,color:#fff;

    subgraph CLI ["CLI ENTRY POINTS"]
        direction TB
        CMD1["command-name━━━━━━━━━━--flag1 --flag2Purpose"]
    end

    subgraph Config ["CONFIGURATION"]
        direction TB
        ENV["Environment Variables━━━━━━━━━━API keys, modes"]
        SETTINGS["Config File━━━━━━━━━━Project config"]
    end

    subgraph Registry ["STATE TRACKING"]
        direction TB
        STATE["State Repository━━━━━━━━━━Active stateProgress"]
    end

    subgraph Monitoring ["OBSERVABILITY"]
        direction TB
        LOGS["Activity Logs━━━━━━━━━━Step-by-step"]
        DEBUG["Debug Artifacts━━━━━━━━━━{{AUTOSKILLIT_TEMP}}/ directory"]
    end

    subgraph Tasks ["TASK COMMANDS"]
        direction TB
        TASK1["task command━━━━━━━━━━Automation"]
    end

    %% FLOWS %%
    CMD1 --> ENV
    ENV --> SETTINGS
    CMD1 --> STATE
    CMD1 --> LOGS
    LOGS --> DEBUG

    %% CLASS ASSIGNMENTS %%
    class CMD1 cli;
    class ENV,SETTINGS phase;
    class STATE stateNode;
    class LOGS,DEBUG output;
    class TASK1 handler;

Color Legend: | Color | Category | Description | |-------|----------|-------------| | Dark Blue | CLI | Command-line entry points | | Purple | Config | Configuration hierarchy | | Teal | Registry | State tracking | | Dark Teal | Monitoring | Observability outputs | | Orange | Tasks | Task automation |

Configuration Hierarchy

| Priority | Source | Example | |----------|--------|---------| | 1 (highest) | Environment | API_KEY=... | | 2 | Secret file | .env.local | | 3 | Config file | config.yaml | | 4 (lowest) | Defaults | Built-in |

Operator Workflows

Create New Work

{command example}

Check Status

{command example}

Reset/Recovery

{command example}

---

## Pre-Diagram Checklist

Before creating the diagram, verify:

- [ ] LOADED `/autoskillit:mermaid` skill using the Skill tool
- [ ] Using ONLY classDef styles from the mermaid skill (no invented colors)
- [ ] Diagram will include a color legend table

---

## Related Skills

- `/autoskillit:make-arch-diag` - Parent skill for lens selection
- `/autoskillit:mermaid` - MUST BE LOADED before creating diagram
- `/autoskillit:arch-lens-development` - For build tooling view
- `/autoskillit:arch-lens-deployment` - For infrastructure view

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [TalonT-Org](https://github.com/TalonT-Org)
- **Source:** [TalonT-Org/AutoSkillit](https://github.com/TalonT-Org/AutoSkillit)
- **License:** MIT

Install and usage instructions live in the source repository linked above.