backlog suggest

    1

    Every suggestion cites the file, line, or commit it came from, it skips anything already tracked, and nothing is filed until you approve it.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    backlog suggest

    Example session with this skill installed

    Scan the /src directory and suggest new issues based on any TODOs or missing error handling you find.

    • Read your context and instructions
    • Compiled the backlog suggest

    I have scanned the /src directory and compared it against the 12 existing open issues. I found 4 items that are not currently tracked in your backlog.

    Proposed GitHub Issues

    #TitleReasonCitation
    1Implement OAuth Refresh LogicFound TODO: handle token expirationsrc/auth/session.ts:42
    2Add Validation to User ProfileController lacks input sanitization found in other routessrc/api/user.ts:115
    3Fix Flaky Integration TestTest is currently marked with @pytest.mark.skipsrc/tests/int_test.py:88
    4Refactor Data ParserHigh churn rate (15 commits in 30 days) suggests latent instabilitysrc/utils/parser.go

    Next steps

    1. Tell me which numbers (e.g., "Create 1 and 3") to push to GitHub.
    2. I will confirm with the new issue URLs once created.
    3. You can then label these as in progress to track them on your board.

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

    About this skill

    Reads your repository and proposes the GitHub issues your backlog is missing: TODO/FIXME comments, stubbed functions, failing or skipped tests, missing tests/CI/docs, and features your README promises but the code lacks. Every suggestion cites the file, line, or commit it came from, it skips anything already tracked, and nothing is filed until you approve it. On a repo with no issues, it seeds a starter backlog. Needs the GitHub CLI. Free and open source (MIT). One of five backlog skills that work together: suggest, order, next, keeper, cleanup. From the maker of Sideboard, a live GitHub Issues board for Claude Code.

    Requires GitHub CLI (gh) authenticated. Only scans local checkouts with a GitHub remote. Cannot track dependencies if the GitHub API returns 404 for the blocked_by endpoint.

    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 1 month ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    The skill performs a smart deduplication check by cross-referencing findings against your open and closed GitHub issues, ensuring it only suggests truly new or unresolved tasks.

    It works with any programming language or framework because it focuses on universal patterns like code comments (TODO/FIXME), README structure, and stubbed logic common across all environments.

    You must have the GitHub CLI (`gh`) installed and authenticated on your local machine, as the skill uses it to sync issue states and create new entries securely.

    No, the skill generates a numbered checklist of proposed issues first, allowing you to review each one and explicitly authorize which ones are pushed to your repository.

    The skill analyzes your `README.md` to identify promised features or documentation headers that lack corresponding implementation in the source code, helping you align your roadmap with reality.

    Yes, the skill is designed to work with any AI agent that has access to your local file system and the ability to execute terminal commands via the GitHub CLI.

    New in Agents & Orchestration