Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    agent standup

    1

    Automate daily standups, weekly reports, and billable timesheets by parsing local AI agent sessions and git history.

    $5

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    Security scanned
    agent standup

    agent standup

    Example session with this skill installed

    I need a weekly report and a timesheet for my work from Monday to today. Check the ~/projects/auth-service repo too.

    • Read your context and instructions
    • Compiled the agent standup
    • Generated the data export

    I have analyzed your local agent sessions and git history from Monday, 2023-10-23, to today. I also scanned the `auth-service` repository for additional commits. Calculated 32.5 hours across 3 projects using a 30-minute gap threshold. ## Weekly Work Report **Project: auth-service** - **Outcomes:** Implemented JWT rotation and updated the user schema to support MFA. Refactored middleware for better error handling. - **Commits:** 14 - **Estimated Time:** 18.25 hours - **Next Week:** Finalize integration tests for the MFA flow and update API documentation. **Project: landing-page** - **Outcomes:** Optimized image assets and fixed CSS grid alignment issues on mobile views. - **Commits:** 6 - **Estimated Time:** 9.75 hours - **Next Week:** Deploy to staging and run lighthouse audits. **Project: internal-tools** - **Outcomes:** Automated the cleanup of temporary build artifacts. (In progress) - **Commits:** 2 - **Estimated Time:** 4.5 hours - **Next Week:** Debug the failure in the cleanup script's cron job. ## Timesheet Summary | Date | Project | Hours | | :--- | :--- | :--- | | 2023-10-23 | auth-service | 7.50 | | 2023-10-24 | auth-service | 6.25 | | 2023-10-25 | landing-page | 5.00 | | 2023-10-26 | landing-page | 4.75 | | 2023-10-27 | auth-service | 4.50 | | 2023-10-27 | internal-tools | 4.50 | | **Total** | | **32.50** | *Note: Hours are estimated by grouping activity blocks and rounding to the nearest quarter hour.* **Next steps** 1. Review the detailed `report.html` in the `./agent-standup` folder for prompt-level details. 2. Open `timesheet.csv` to import this data into your billing software. 3. Let me know if you need to adjust the tone for a client email or a manager's Slack message.

    report.html

    CSV · data export

    Generated

    Example file from a real run - the skill writes it into your workspace.

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

    About this skill

    Logging manual hours for agent-led development is a friction point that leads to inaccurate billing and missed status updates. This skill automates the extraction of work history from local coding agents like Claude Code, Codex, and Gemini CLI, alongside git commit history. It generates structured reports and timesheets based on actual machine activity. ## What it does - **Data aggregation** reads local session files, command history, and git commits across multiple repositories. - **Time estimation** calculates work blocks based on activity gaps and rounds to the nearest quarter hour for billing. - **Automated reporting** generates standup notes, weekly status reports, and visual HTML summaries. - **Project mapping** groups prompts, file edits, and commits by project folder to distinguish between client work. - **Timesheet generation** outputs CSV files with date, project, and hour breakdowns for financial tracking. ## How it works 1. **Identify range** by mapping user requests like "what did I do yesterday" to specific date parameters and output formats. 2. **Execute collection** using the provided scripts to parse local agent sessions and redact sensitive strings. 3. **Draft the report** by summarizing prompts into outcomes and grounding every claim in a commit or file edit. 4. **Deliver files** by providing the chat summary and file paths for `standup.md`, `timesheet.csv`, and `report.html`. ## Frameworks & tools The tool requires Node.js 18+ and git. It is compatible with Windows, macOS, and Linux, specifically targeting local CLI agents including Claude Code, Codex CLI, and Gemini CLI. ## Why this beats prompting it yourself Generic prompts cannot access your local file system to parse proprietary agent session formats or calculate precise time gaps between CLI commands. This skill uses a dedicated script to bridge the gap between your terminal history and your status reports, ensuring data-driven accuracy. ## Use cases - Generating daily standup notes based on yesterday's actual terminal activity. - Calculating billable hours per project for client invoicing and timesheets. - Summarizing weekly progress for managers by grouping commits and edited files. - Auditing agent-led work to see which commands or prompts caused blockers. ## Known limitations Only sessions stored on the local machine are accessible; browser-based chats or work on other devices are excluded. Changes in third-party CLI session formats may cause parsing skips.

    How to use

    Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean 3 days ago

    • Passed all security checks, Safe to install

    Listed3 days ago

    What's inside

    Frequently Asked Questions