Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    PR Risk Reviewer

    1

    Perform structured risk assessments on code diffs to identify security flaws, breaking changes, and deployment risks.

    Free

    1 useSecurity scanned
    PR Risk Reviewer

    PR Risk Reviewer

    Example session with this skill installed

    Review this PR for risk: https://github.com/acme/backend/pull/402. It changes the payment gateway timeout logic and adds a migration to the orders table.

    • Read your context and instructions
    • Compiled the pr risk reviewer

    I have analyzed the diff for acme/backend/pull/402. The analysis flagged two critical paths: the orders migration and the gateways/stripe.py timeout logic.

    PR Risk Assessment: PR #402

    Verdict: MEDIUM RISK

    The primary risk is potential request accumulation due to increased timeouts, which could saturate the worker pool during peak traffic. The migration is additive and safe for concurrent execution.

    Top Risks

    Worker Saturation [High]: gateways/stripe.py:42. Increasing request_timeout from 5s to 30s without a corresponding increase in worker capacity may lead to exhaustion during Stripe outages.

    Database Lock [Low]: migrations/0042_add_retry_count.py:15. Adding a nullable column to orders. Low risk as it does not require a full table rewrite in Postgres.

    Risk Dimension Scoring

    DimensionScoreNotes
    Data SafetyLowAdditive migration, no data transformation.
    Breaking ChangesNoneInternal logic change only; no API contract changes.
    SecurityLowNo new user inputs or auth changes detected.
    ComplexityMediumChanges core payment flow error handling.

    Pre-Merge Test Plan

    1. Migration Check: Run python manage.py migrate on a staging DB with >1M rows to verify migration time.

    Timeout Simulation: Use a mock server to induce a 25s delay in the Stripe API and monitor Celery worker availability.
    3.

    Idempotency Test: Trigger a timeout during an order update and verify no duplicate order_id entries are created.

    Rollback Plan

    • Code: Revert to commit a1b2c3d and redeploy.

    Database: Migration is additive; no immediate rollback required, but 0042 can be reversed if necessary via migrate orders 0041.

    Next steps

    • Verify if CELERY_WORKER_CONCURRENCY needs adjustment for longer-running tasks.
    • Confirm the Stripe timeout value with the infrastructure team.

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

    About this skill

    PRs move fast, and critical regressions often hide in the noise of large diffs. This skill audits code changes specifically for stability, security, and operational risk rather than just syntax or style. It identifies high-impact changes like database migrations, API contract breaks, and auth logic shifts that standard linters miss.

    What it does

    • Risk Scoring provides a structured verdict based on ten dimensions of operational risk.
    • Automated Triage flags sensitive files including lockfiles, infrastructure config, and payment logic.
    • Evidence-Based Auditing maps every medium to high risk finding to specific file paths and line numbers.
    • Test Planning generates concrete verification steps including specific inputs, user roles, and expected results.
    • Rollback Strategy defines how to revert the change if the deployment fails in production.

    How it works

    1. Input Diff: The user provides a git diff, patch file, or a GitHub PR URL to be fetched.
    2. Signal Gathering: The skill runs an internal analysis script to calculate diff stats and flag risky patterns.
    3. Deep Analysis: Targeted files are reviewed against specific security and Python-stack rubrics.
    4. Report Generation: A structured risk report is produced, highlighting top concerns and a final merge verdict.

    Frameworks & tools

    Built for teams using Git, GitHub, and Python backends (Django, FastAPI, SQLAlchemy, Alembic). It utilizes custom scripts for diff parsing and scoring rubrics for consistent assessment.

    Why this beats prompting it yourself

    Generic prompts often miss silent logic changes or focus too much on code style. This skill enforces evidence-based reporting and applies a rigorous rubric to ensure findings are objective and actionable for the person merging the code.

    Use cases

    • Auditing complex database migrations for potential locking or data loss.
    • Reviewing sensitive auth or security changes before they hit production.
    • Assessing the blast radius of dependency bumps in large Python projects.
    • Providing a final sanity check for high-stakes releases.

    Known limitations

    The skill reviews code diffs, not the full running system, so it cannot detect environment-specific runtime issues. Performance is best on PRs under 2,000 lines.

    Analyzes diffs only, not the full runtime state. Confidence decreases for partial diffs or changes exceeding 2,000 lines. Network access is required for fetching GitHub URLs.

    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

    GitHub

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Environment Variables

    Allowed Hosts

    github.com
    api.github.com
    Listed29 days ago

    What's inside

    Frequently Asked Questions

    This skill focuses exclusively on operational and security risks, such as database locks, API breaking changes, and auth logic shifts, whereas standard tools typically focus on syntax, formatting, and style.

    The 'pr risk reviewer' is optimized for Python-based backends using frameworks like Django, FastAPI, SQLAlchemy, and Alembic, though it can provide general risk assessments for most Git-based projects.

    While it can analyze any git diff, the skill is most effective on pull requests under 2,000 lines to ensure the analysis remains deep and doesn't miss subtle logic regressions.

    Upon purchase, you receive the skill configuration, the proprietary risk scoring rubrics, and the internal analysis scripts required to process and audit your diffs.

    The skill generates a structured report that includes a multi-dimensional risk score, a test plan for verification, and a specific rollback strategy to mitigate deployment failures.

    No, this skill analyzes the code diff statically and does not require access to your production environment or secrets to perform its risk assessment.

    New in Code Quality & Review