Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    Local Projects Inventory Table

    3

    Scans every top-level subfolder of a target directory (defaults to ~/Projects) and builds one row per folder.

    $6.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Local Projects Inventory Table

    Local Projects Inventory Table

    Example session with this skill installed

    Survey everything in my ~/Projects folder

    • Read your context and instructions
    • Compiled the local projects inventory
    • Generated the data export

    Surveyed 6 top-level folders under ~/Projects. Full breakdown below, sorted by most recently touched.

    ~/Projects overview — generated 2026-08-27, sorted by latest change (most recent first)

    Last Changed = last git commit date if the folder is a git repo, otherwise the newest file's modification date, with a relative-time label (today/yesterday/N days/months/years ago) alongside it.

    Created = folder's filesystem creation date (for a git clone, this is when it was cloned locally, not the upstream project's origin; "unknown" if the filesystem doesn't track birth time).

    Local Changes = true if the repo has any uncommitted (modified/staged/untracked) files, or if the folder has no git repo at all (nothing can be "committed" without one).

    Size = total disk usage (du -sh) of the folder, including .git/node_modules/venv/build artifacts — not source-code size alone.

    Total Chars = character count across all non-binary files in the folder (content volume, not disk bytes).

    Code Chars = same, restricted to recognized source-code file extensions only — how much of Total Chars is actual code.

    Has Creds = best-effort heuristic flag (filename + content pattern match) for anything that LOOKS like a credential/secret. false is not a guarantee — it means no configured pattern matched, not that the folder was audited exhaustively.

    FolderDescriptionLast ChangedCreatedSizeTotal CharsCode CharsGit?Local ChangesHas Creds
    invoice-botPurpose: Telegram bot that logs supplier invoices, extracts totals via OCR, and posts a daily summary to a private channel.<br>Stack: Python (python-telegram-bot, pytesseract, SQLAlchemy)<br>Calls: Telegram Bot API2026-08-25 (2 days ago)2026-03-1042M18500096000yestruetrue
    weather-dashboardPurpose: React dashboard that plots a 10-day weather forecast for saved locations.<br>Stack: JavaScript (React, Recharts, Axios)<br>Calls: OpenWeatherMap API2026-08-20 (7 days ago)2026-01-15210M340000128000yesfalsefalse
    r-forecast-toolkitPurpose: An R package providing time-series forecasting helpers — rolling means, seasonal decomposition, backtesting.<br>Stack: R (forecast, dplyr, purrr)<br>Calls: none detected2026-07-30 (28 days ago)2025-11-0218M9500061000yesfalsefalse
    scrape-experimentsPurpose: Standalone scripts that scrape product prices from a handful of retailer sites into CSV files.<br>Stack: Python (requests, beautifulsoup4)<br>Calls: none detected2026-06-18 (2 months ago)2026-06-183.2M2100018500notruefalse
    old-notesNon-code asset folder — contains: meeting_notes.md, roadmap_2025.pdf, ideas.txt, archive/, misc/2025-09-02 (11 months ago)2024-05-01640K62000notruefalse
    brand-assetsNon-code asset folder — contains: logos/, screenshots/, brand_guide.pdf, raw_data.csv2024-11-05 (1 years ago)2024-11-051.8G00notruefalse

    ────────────────────────────────────────
    Survey saved to: ~/Projects/repos_overview.txt
    6 folders surveyed — 3 with git, 3 without. 4 have uncommitted local changes. 1 flagged for possible credentials.
    ────────────────────────────────────────

    Next steps

    1. Review invoice-bot for potential leaked credentials flagged by the heuristic scan.
    2. Commit or stash the uncommitted changes in scrape-experiments.
    3. old-notes and brand-assets haven't been touched in 11+ months and aren't git-tracked — worth archiving elsewhere or deleting if they're no longer needed.

    roadmap_2025.pdf

    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

    The problem

    When a dozen or more project folders pile up under one directory, there's no quick way to tell what each one actually is, what it's built with, when it was last touched, whether it's still under version control, or whether it's quietly sitting on a leaked API key - short of opening every single folder by hand.

    What it does

    • Scans every top-level subfolder of a target directory (defaults to ~/Projects) and builds one row per folder.
    • Derives a Purpose/Stack/Calls description for each folder from its README, package.json, DESCRIPTION, or SKILL.md - falling back to reading the actual source code when none of those exist.
    • Computes git status, last-changed date (with a relative-time label like "7 months ago"), folder creation date, disk size, and total/code character counts for each folder using git log, git status, du, find, wc, and stat.
    • Flags folders that look like they contain credentials or secrets via filename and content pattern matching, without ever printing the matched value.

    Why this beats prompting it yourself

    A one-off prompt like "summarize my Projects folder" tends to guess at what a folder does from its name, skip the git/date/size computation entirely, and either miss real secrets or accidentally print the matched key in its output. This skill's fixed procedure only ever states a purpose it actually read from a README or source file, computes every date/size/count from an exact command rather than eyeballing it, and reduces the credentials check to a true/false flag with the matched value never surfaced.

    Use cases

    • Getting oriented in a Projects folder you haven't fully looked at in months, to decide what's worth reviving, archiving, or deleting.
    • Auditing a personal or team machine for repos with uncommitted local changes before a backup or migration.
    • Running a quick pass for accidentally-committed credentials across every local project folder.
    • Building a standing inventory table to paste into a status doc or onboarding note for a new machine.

    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

    Money-back guarantee

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

    Trust & safety

    Security scanned

    Verified clean 1 month ago

    • Passed all security checks, Safe to install

    Requires

    Python

    Listed1 month ago

    What's inside

    Frequently Asked Questions