Well Run Software

    1

    Audit any repo or set up the practices that keep software shipping safely: CI, rulesets, hooks, strict lint, secrets, supply chain.

    $9

    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 CLIMuseMuseDotsDots+21 more

    About this skill

    One idea behind everything here: make the right thing the easy thing, and the wrong thing impossible. Prefer a control that tooling enforces over a rule people must remember.

    User wantsMode
    "Audit this repo", "what are we missing", "is this well run"Audit
    "Set up a new project", "add CI", "harden this repo"Setup
    A question about one practice ("how should we do code review?")Advise: answer from references/playbook.md, the matching section only
    1. Run the checker from the repo root:
      bash <skill-dir>/scripts/audit.sh .
      
      It checks files, workflows and (if gh is logged in) branch protection. It prints PASS/WARN/FAIL/SKIP lines and exits non-zero on any FAIL.
    2. The script covers only what a file scan can see. Then check by hand what it cannot, using references/playbook.md:
      • Are tests real? Pick the riskiest check (auth, permissions) and break it on purpose. Does a test fail?
      • Does anything log, print or ship a secret? Grep logging calls, and anything shipped to users (web bundles, mobile builds, binaries, published packages).
      • Is deploy or release automated, and is rollback known?
      • For running services: is there error tracking and uptime monitoring?
      • Skip any practice that does not fit what this is (a library has no deploys, a CLI has no uptime). Say which you skipped.
    3. Report findings ranked by risk, not by section order. Use this priority:
      1. Secrets exposed (committed, logged, or shipped to users)
      2. Anyone can push to main unreviewed, or admins bypass protection
      3. No CI gate, or CI not a required check
      4. Supply chain gaps: unpinned actions, no lockfile, no dependency updates
      5. Missing tests on security boundaries
      6. Everything else
    4. For each finding give: what is wrong, why it matters (one line), the exact fix. End with the 9-question self-audit from the playbook, answered for this repo where you can tell.

    Do not change anything in Audit mode unless the user asks.

    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

    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 27 days ago

    Requires

    Node.js
    Python
    lint-staged

    Permissions

    Terminal / Shell
    Listed27 days ago

    What's inside

    Frequently Asked Questions

    Audit any repo or set up the practices that keep software shipping safely: CI, rulesets, hooks, strict lint, secrets, supply chain.

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use well-run-software on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.

    New in DevOps & Cloud