agentic-best-practices

Execute safe Git workflows — branching, committing, resolving conflicts, and managing PRs

Use when controlling AI spend, token budgets, model routing, or workflow efficiency before scaling usage

Use when handling incidents, outages, severe regressions, or operational emergencies before attempting broad fixes

Use when investigating latency, throughput, resource saturation, or performance regressions before changing implementation details

Use when reviewing code, preparing a PR for review, or processing review feedback

Use when diagnosing bugs, test failures, or unexpected behavior before attempting any fix

Plan and execute safe deployments with rollback procedures, verification, and monitoring

Use when code changes may affect documentation, when adding new features that need docs, or when reviewing documentation freshness

Use when writing end-to-end tests, designing E2E test strategy, or debugging flaky E2E tests

Write clear, actionable bug reports and feature requests that humans and agents can act on immediately

Implement structured, secure logging with proper levels, correlation IDs, and redaction

Use when planning multi-step tasks, writing implementation plans, or starting new feature work before touching code

Use when creating PRs, writing commit messages, managing branches, or preparing code for merge

Use when crafting prompts for AI tools, managing context in AI conversations, or decomposing tasks for AI

Use when coordinating large changes across multiple files or performing significant code restructuring

Use when writing security-sensitive code, handling authentication, processing user input, or managing secrets

Use when writing tests, designing test strategy, or verifying AI-generated code