evidence upgrade planner

    1

    Plan and carry out dependency upgrades without breaking the build.

    $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 CLIDeepSeekDeepSeekMuseMuse+22 more

    evidence upgrade planner

    Example session with this skill installed

    Plan an upgrade for the 'request' library to 'axios' in this project, or just bump 'request' if there is a security fix. Check for breaking changes and affected files.

    • Read your context and instructions
    • Compiled the evidence upgrade planner

    I have analyzed the manifest files and existing test results. The request library is deprecated and contains three high-severity CVEs. Since request is no longer maintained, a patch is not available, and a migration to axios is required.

    Upgrade Plan: request to axios

    PackageFromToReasonRiskBreaking ChangesAffected CodeCheckRollback
    request2.88.2axios 1.6.0Deprecation & CVE-2023-28155HighAPI change: .get() returns promise vs callbacksrc/api/client.js:42, src/auth.js:12npm testnpm install request@2.88.2
    @types/request2.48.0(removed)CleanupLowTypes no longer neededN/Atsc --noEmitnpm install @types/request

    Impact Analysis

    • Source: Axios Migration Guide (v1.x).

    Verified Hits: Found 12 call sites using the callback pattern in src/api/client.js. These must be converted to async/await.

    Trap Found: The current project uses CommonJS, while Axios 1.x defaults to ESM-friendly exports. Verified that require('axios') still works in current Node runtime.

    Execution Results

    1. Baseline Check: npm test passed (24/24 tests).
    2. Step 1: Run npm uninstall request @types/request && npm install axios. Result: SUCCESS.
    3. Step 2: Refactor src/api/client.js to use Promise-based calls. Result: PLANNED, NOT RUN.

    Unverified List

    • Potential memory leak in Axios under Node 14.x (Source: community thread, not official changelog).

    Recommendation

    Confidence

    Medium. The API surface used is small, but the switch from callbacks to promises requires manual refactoring of the internal API client.

    Next steps

    1. Execute the refactoring of src/api/client.js to handle promises.
    2. Run the integration test suite specifically for the ExternalAPI class.
    3. Commit changes once npm test returns green.

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

    About this skill

    Plan and carry out dependency upgrades without breaking the build. Every breaking-change claim is tied to a source, every affected call site is found in your code, and each step has a check and a way back. Use for major version bumps, CVE patches, framework migrations, and clearing out stale packages.

    What it does

    • Evidence verification ties every breaking change claim to specific release notes or migration guides.
    • Impact mapping searches your codebase for imports, call sites, and config keys affected by the upgrade.
    • Baseline validation runs existing tests and builds to check whether you are starting from a broken state.
    • Conflict screening detects peer-dependency traps, engine-range mismatches, and module-format switches.
    • Execution sequencing orders updates into discrete steps with individual rollback commands and success checks.

    How it works

    1. Establish ground truth by reading manifests and lockfiles to record exact resolved versions.
    2. Screen for traps like changed defaults, renamed packages, and raised runtime floors.
    3. Map the impact by searching for the overlap between documented breaking changes and your actual code.
    4. Define specific check and rollback commands for each isolated step.

    Frameworks & tools

    Works with any package manager including npm, pip, cargo, and go. It relies on standard CLI tools like npm outdated or cargo outdated and interprets manifest files like package.json, requirements.txt, and Cargo.toml.

    Use cases

    • Major version migrations where framework plugins and peer dependencies must move together.
    • CVE patching to find the smallest version bump that fixes a vulnerability.
    • Technical debt clearing by identifying and removing stale or unused packages.
    • Runtime upgrades to check codebase compatibility before dropping support for older Node or Python versions.

    Known limitations

    If the agent cannot run shell commands, the plan is marked as UNEXECUTED and relies solely on static file analysis. High-risk upgrades require a pre-existing test suite to check behavior.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.

    Requires access to manifests and lockfiles. If CLI tools cannot be run, plans are marked UNEXECUTED. Success depends on the quality of the project's existing test suite for behavior checks.

    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 buying a skill.

    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 2 days ago

    Permissions

    Write Files
    Listed2 days ago

    What's inside

    Frequently Asked Questions

    The skill is compatible with any agent capable of file system access and shell execution, supporting major package managers like npm, pip, cargo, and go.

    While the skill provides the plan and rollback commands, it requires a pre-existing test suite in your project to verify that the upgraded code functions correctly at runtime.

    The planner performs a 'baseline validation' to ensure your current environment is stable before proposing changes, preventing you from inheriting existing bugs during a migration.

    You receive the complete skill logic for evidence-based planning, impact mapping templates, and a set of execution sequences for various package managers.

    Yes, the skill is specifically designed to handle complex peer-dependency traps and engine-range mismatches that often occur during major version migrations.

    New in LLM Ops