Agent Session Observatory

    1

    See every local Claude Code and Codex session, what it is doing, and what is waiting on you, on Mac, Windows, and Linux, plus any other agent's logs through a generic adapter.

    $25

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Agent Session Observatory

    Example session with this skill installed

    Run a session summary for the last 48 hours and show me what is waiting.

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

    Found 4 active sessions in the last 48 hours. One session is currently waiting for your input.

    Agent Session Summary

    StatusAgentProjectLast ActiveContextNotes
    WAITINGClaudeweb-portal12 mins ago64%Asks: "Should I proceed with deleting the deprecated /v1/auth endpoint?"
    WORKINGCodexdata-pipeline2 mins ago12%Now: Running pytest tests/test_ingestion.py
    IDLEClaudedocs-site5 hours ago5%Last: Finished updating README.md
    WORKINGCursorinfra-aws1 min agoN/ALast text: "Scanning terraform state for orphaned resources"

    Current Fleet Status

    • Waiting: 1
    • Working: 2
    • Idle: 1

    Next steps

    • Address the deletion prompt in the web-portal project terminal.
    • Check the data-pipeline test results in approximately 5 minutes.
    • Use python3 -I collect-session.py --json --out report.json to export this data for your dashboard.
    Finished updating README.md

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

    About this skill

    Running multiple coding agents in parallel makes it impossible to track which terminal is stuck. This skill scans your local logs to surface sessions waiting for human input, ensuring you never leave an agent idling for hours.

    What it does

    • Identifies blockers by scanning logs for questions, approval requests, or decisions that require human intervention.
    • Summarizes active sessions across Claude Code and Codex, including project name, title, model, and last activity timestamp.
    • Monitors progress by reporting what each working session is doing right now, including its current task, last steps, and plan.
    • Tracks resource usage by extracting context window percentages and rate limit windows from local metadata.
    • Supports external agents through a generic adapter that parses any .jsonl session log from tools like Cursor or Copilot.

    How it works

    1. Run python3 -I collect-session.py to print a summary of all active, waiting, and idle sessions to your terminal.
    2. Use the --hours flag to adjust the lookback window for finding older sessions.
    3. Invoke --json to output session data for custom dashboards or internal tooling.
    4. Set environment variables like AGENT_OS_CLAUDE_DIR to point the scanner at non-standard log locations.

    Frameworks & tools

    Built with Python 3.11+ using only the standard library. It interfaces with Claude Code and Codex log files on macOS, Windows, and Linux.

    Why this beats prompting it yourself

    An agent cannot see what other agents are doing in separate terminal instances or processes. This skill operates at the OS level, reading the physical log files that LLMs cannot access themselves to provide a unified view of your entire agent fleet.

    Use cases

    • Find which of five parallel Claude Code tasks is waiting for a test suite approval.
    • Check the remaining rate limit quota for Codex sessions before starting a large refactor.
    • Monitor long-running agent tasks without constantly switching terminal tabs.

    Known limitations

    Cannot track agents that do not write local .jsonl logs. Requires Python 3.11 or newer. Context and rate limit data depend entirely on what the specific agent writes to its local metadata files.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Requires Python 3.11+. Only works with agents that write local .jsonl logs. Mac/Windows testing is pending; currently verified on Linux.

    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 buying a skill.

    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

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 8 days ago

    Software
    Python 3.11Python 3PowerShell

    Permissions

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

    What's inside

    Frequently Asked Questions

    It solves 'terminal fatigue' by scanning your local logs to find agents that are stuck waiting for your permission or input, preventing agents from sitting idle for hours while you are busy in another tab.

    The skill natively supports Claude Code and Codex, but includes a generic adapter that can parse .jsonl session logs from other tools like Cursor or Copilot if they are saved locally.

    No, this tool operates at the OS level by reading local log files; it does not require an API key or an active internet connection to summarize your agent activity.

    You receive the core Python utility script, documentation for environment variable configuration, and the generic adapter for integrating third-party agent logs.

    By default, it scans for active sessions, but you can use the `--hours` flag to look back further and the `--json` flag to export data for your own custom monitoring tools.

    The tool requires Python 3.11 or newer and access to the directories where your agents store their log files, which can be customized via environment variables.

    New in Agents & Orchestration