More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Todosweep: every TODO found, ranked and triaged

    1

    Finds TODO, FIXME, HACK and BUG comments, ranks them by urgency, and flags stale ones with git blame. It lists only: you decide what to fix.

    Free

    1 useSecurity scanned
    Todosweep: every TODO found, ranked and triaged

    Todosweep: every TODO found, ranked and triaged

    Example session with this skill installed

    Todosweep src/: only stale ones, just the BUGs and FIXMEs

    • Read your context and instructions
    • Compiled the todosweep

    I scanned src/ for stale BUG and FIXME tags. I found 3 items that have been in the codebase for more than 30 days.

    3 Stale TODOs found in src/

    πŸ”΄ High Priority (BUG)
    ─────────────────────
    src/auth/session.ts:88: BUG: session token does not clear on manual logout in Firefox
    Author: alice-dev, 45 days ago [STALE]

    🟑 Medium Priority (FIXME)
    ─────────────────────
    src/api/client.ts:112: FIXME: exponential backoff not implemented for 503 errors
    Author: bob-engineer, 62 days ago [STALE]

    src/components/DataGrid.tsx:45: FIXME: flickering on initial load when dataset exceeds 100 rows
    Author: alice-dev, 38 days ago [STALE]

    SUMMARY

    • 1 high (BUG)
    • 2 medium (FIXME)
    • 3 stale (>30 days)

    TRIAGE SUGGESTIONS

    Address now

    src/auth/session.ts:88: This is a security-related bug (Firefox logout) that has been open for 45 days. It should be prioritized for the next patch.

    Decide and act

    src/api/client.ts:112: The lack of backoff is technical debt. If the API is stable, document this in the README or move to a Jira ticket.

    src/components/DataGrid.tsx:45: UI flicker is a UX issue. Check if a recent library update fixed this; if not, schedule a refactor.

    Next steps

    • Run Rootcause on src/auth/session.ts to investigate the Firefox session clearing bug.
    • Convert the FIXME in DataGrid.tsx into a formal issue if it won't be fixed this sprint.

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

    About this skill

    Codebases inevitably accumulate TODO, FIXME, and HACK comments that eventually turn into invisible technical debt. This skill scans your repository to extract, categorize, and triage these markers, providing a clear map of what needs immediate fixing versus what can be safely ignored or deleted.

    What it does

    • Multi-tag extraction scans for TODO, FIXME, HACK, BUG, XXX, NOTE, and WARNING tags across your files.
    • Urgency triaging automatically ranks findings into High, Medium, Low, and Info categories based on tag type.
    • Git integration uses git blame to show who last edited each line and how long ago.
    • Stale detection flags lines untouched for more than 30 days as stale to help identify forgotten or irrelevant tasks.
    • Contextual filtering allows narrowing scans by subfolders, specific files, authors, or tag types.

    How it works

    1. Targeting: Specify a directory or file using Todosweep <path>.
    2. Filtering: Refine the results by adding criteria like "only stale ones" or "by author-name".
    3. Analysis: The skill runs a scan while ignoring node_modules and build directories.
    4. Triage: Review the prioritized list and specific suggestions for addressing, converting, or deleting items.

    Frameworks & tools

    This tool relies on git blame for metadata and works across any language that uses standard comment syntax, including TypeScript, JavaScript, Python, and Go.

    Why this beats prompting it yourself

    Generic prompts often miss the specific urgency hierarchy and fail to integrate git blame data for age-based triaging. This skill enforces a structured output that separates high-risk bugs from low-priority notes while automatically filtering out noise from vendor directories.

    Use cases

    • Release preparation to ensure no BUG or FIXME tags remain in the production path.
    • Tech debt audits to identify HACK comments that have been stale for months.
    • Onboarding to quickly map out the known issues and architectural warnings in a new codebase.

    Known limitations

    Scans only code comments and skips documentation files by default. Age calculation is based on the last time the specific line was edited, not necessarily when the comment was first created.

    Skips Markdown and documentation files by default. Relies on git blame for age calculation. Focuses on code comments, ignoring node_modules and build folders.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 29 days ago

    • Free with an Agensi account

    Requires

    Git

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed29 days ago

    What's inside

    Frequently Asked Questions

    It works with any language that uses standard comment syntax, provided the repository is tracked by Git for metadata extraction.

    This skill automatically ignores common vendor and build directories like `node_modules`. You can further refine your scan by specifying subfolders, specific files, or asking in plain language for one author or one tag type.

    The skill uses `git blame` to determine when a line was last modified. If that line has not been edited for more than 30 days, it is flagged as 'stale' to help you identify technical debt that may no longer be relevant.

    You will receive the full 'Todosweep' skill package, including the logic for multi-tag extraction, the urgency triaging framework, and the git blame steps for author and age.

    No complex setup is required; once the skill is added to your AI agent, you ask it to scan a local repository path, such as `src/`.

    New in Code Quality & Review