Agent Session Observatory Lite

    1

    Free lite version, session summary only, no question text, no context percent.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Agent Session Observatory Lite

    Example session with this skill installed

    Run a session summary for the last 24 hours to see which Claude Code tasks are waiting for me.

    • Read your context and instructions
    • Compiled the agent session observatory

    I have scanned your local log directories for Claude Code and Codex sessions from the last 24 hours. Below is the summary of active and recently modified sessions.

    Agent Session Summary

    VendorProject / TitleStatusModelLast Active
    Clauderefactor-auth-logicWAITINGclaude-3-7-sonnet2 mins ago
    Claudeunit-test-api-v2WORKINGclaude-3-7-sonnet10 secs ago
    Codexschema-migration-sqlIDLEcodex-latest5 hours ago
    Genericdocs-update-workflowDONEgpt-4o1 hour ago
    Claudecss-fix-sidebarWAITINGclaude-3-5-sonnet15 mins ago

    Next steps

    1. Resume the refactor-auth-logic session to answer the pending architect question.
    2. Check the css-fix-sidebar session as it has been waiting for over 15 minutes.
    3. Run python3 -I session-summary.py --json if you need to export this table for your personal dashboard.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Context switching between multiple local agents is slow and manual. This skill eliminates the friction of hunting through log directories to find which background tasks are finished or stalled. It provides a lightweight, local-only dashboard for developers managing concurrent agent workflows.

    What it does

    • Status tracking identifies if sessions are currently working, waiting for user input, idle, or completed.
    • Multi-agent support natively parses logs from Claude Code and Codex while providing a generic adapter for other .jsonl sources.
    • Cross-platform compatibility operates on Mac, Windows, and Linux using only the Python standard library.
    • Log aggregation collects session titles, model types, and activity timestamps into a single terminal view.
    • Privacy-first reporting truncates sensitive text and shortens home paths without uploading data or making network calls.

    How it works

    1. Run python3 -I session-summary.py to get a high-level list of all active and recent agent sessions.
    2. Use the --hours flag to filter logs from a specific timeframe, such as the last 72 hours.
    3. Pass the --json flag to output machine-readable data for integration with other local CLI tools.
    4. Point the script at custom log locations using environment variables like AGENT_OS_LOG_DIRS.

    Frameworks & tools

    Built with Python 3.11+ using the standard library only. It integrates with Claude Code, Codex, and any agent that exports to .jsonl formats.

    Why this beats prompting it yourself

    Parsing nested, concurrent .jsonl log files manually is error-prone and tedious. This tool provides a deterministic, zero-dependency script that extracts status logic that a standard LLM prompt cannot access without being fed the entire raw log directory.

    Use cases

    • Identify which background Claude Code task is waiting for a prompt after you stepped away.
    • Audit which models were used across different local projects for cost or performance tracking.
    • Monitor long-running Codex sessions to ensure they haven't timed out or gone idle.

    Known limitations

    Requires Python 3.11 or newer. It cannot display question text or tool call counts as those features are reserved for the full version. Local log access is required.

    Requires Python 3.11+. Does not display session questions, tool call counts, or live status line captures. Local log access is mandatory.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 8 days ago

    • Free with an Agensi account

    Requires

    Python 3.11 or newer, standard library only, no extra packages, no network, no account. Mac: python3. Windows: py -3 in PowerShell. Linux: python3.
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Listed8 days ago

    What's inside

    Frequently Asked Questions

    It provides a centralized terminal dashboard that monitors log files from multiple local AI agents, instantly showing you which tasks are active, stalled, or awaiting your input without you having to manually search through directories.

    The tool is built to natively parse logs from Claude Code and Codex, but it also includes a generic adapter for any other agent that exports activity to the .jsonl format.

    No, this is a privacy-first, local-only script that uses the Python standard library to process logs on your machine; it never uploads your data or makes external network calls.

    This skill requires Python 3.11 or newer and functions across Mac, Windows, and Linux, provided you have local read access to the directories where your agents store their logs.

    The Lite version provides session titles, model types, timestamps, and status tracking; however, it does not include the detailed question text or tool call counts found in the full version.

    Setup is minimal: simply run the Python script via your terminal and, if necessary, point it to your custom log directories using the AGENT_OS_LOG_DIRS environment variable.

    New in Agents & Orchestration