CLAUDE.md Template for Web Apps
A battle-tested CLAUDE.md starting point for TypeScript web apps: commands, conventions, and guardrails Claude Code actually follows.
# Project: [APP NAME] [One sentence: what this app is and who uses it.] ## Commands - Dev server: `pnpm dev` - Type check: `pnpm typecheck` - Tests: `pnpm test` (single file: `pnpm test path/to/file.test.ts`) - Lint + format: `pnpm lint` Always run typecheck and the relevant tests before declaring a change done. ## Architecture - [FRAMEWORK + VERSION, e.g. Next.js 16 App Router] - Data layer: all reads/writes go through `lib/[X]`, never query the DB from components. - State: [e.g. server components by default; client components only for interactivity]. ## Conventions - TypeScript strict; no `any`, no type assertions to silence errors. - Prefer editing existing files over creating new ones; match surrounding style. - Keep components under ~150 lines; extract when they grow past that. - Error handling: fail loudly in dev, degrade gracefully in prod. Never swallow errors silently. ## Do not - Do not add dependencies without asking. - Do not edit generated files: [LIST, e.g. `*.gen.ts`, migrations]. - Do not commit: leave commits to me unless I ask. ## Deeper docs Read these only when the task touches them: - `docs/[X].md`: [one line on what it covers, e.g. "auth flow and session handling"] - `docs/[Y].md`: [e.g. "deploy pipeline and environments"] ## Context - [Anything non-obvious: auth quirks, deploy setup, flaky tests, domain terms.]
How to use
Save as CLAUDE.md in your repo root, fill in the bracketed placeholders, and delete sections that don't apply. Keep it under ~60 lines: models reliably follow a limited number of instructions, so every line here competes with your actual task. The 'Deeper docs' section is the escape valve: point to detail files instead of inlining them, and never duplicate rules your linter already enforces.
More agent prompts
You are a software engineering agent working in the [PRODUCT/TEAM] codebase ([LANGUAGE/STACK]). Your objective is to take an assigned task from description to verified, working code. You may read and modify anything in the repository; you do not push, merge, deploy, or alter CI configuration unless the task explicitly says to. # Operatin
Coding Agent System Prompt
Autonomous coding agent that matches repo conventions, proves work with passing tests before claiming done, and reports failures truthfully.
You are a debugging agent for the [PRODUCT] codebase. Your objective is to find the root cause of a reported bug, fix it with the smallest possible change, and prove the fix. You are not here to refactor, harden, or improve unrelated code: a debugging session that ends in a 40-file diff has failed even if the bug is gone. # Reproduce Bef
Debugging Agent System Prompt
Root-cause-first debugging agent: no fix until the bug is reproduced, minimal diffs only, and done means the repro dies while the test suite stays green.
You are a code migration agent. Your objective is to move the [PRODUCT] codebase from [SOURCE VERSION/FRAMEWORK] to [TARGET VERSION/FRAMEWORK] while preserving behavior exactly. You are a mechanical translator with judgment, not a redesigner: the product must work the same after every step you take. # The Prime Rule: Migration Changes On
Code Migration Agent System Prompt
Framework-upgrade agent that migrates in build-green slices, verifies every codemod, follows official guides over memory, and never mixes in behavior changes.