Skip to content
Agentmart
Submit a tool

CLAUDE.md · Hiram-Wong/zyfun

CLAUDE.md from Hiram-Wong/zyfun: 89 lines covering Guiding Principles (MUST FOLLOW), Development, Conventions, Security.

Template by Hiram-Wong

IndexedAGPL-3.0★ 9,075
Write a review

Chalk Labs

Need help deploying CLAUDE.md · Hiram-Wong/zyfun?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code. Read the repository before you give any tool access to your data.

curl -fsSL https://raw.githubusercontent.com/Hiram-Wong/zyfun/main/CLAUDE.md -o CLAUDE.md

Read it and adapt it to your project before use.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

The CLAUDE.md file that Hiram-Wong/zyfun (9,075 stars) keeps for coding agents. It has 89 lines in 4 sections: Guiding Principles (MUST FOLLOW); Development; Conventions; Security. Use it as a model for your own project's instructions.

Use cases: prompt-engineering

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

What's in it

A CLAUDE.md file: project memory Claude Code loads at the start of every session.

For
Claude Code
Length
89 lines
File
CLAUDE.md

Sections

  1. Guiding Principles (MUST FOLLOW)
  2. Development
  3. Conventions
  4. Security

First lines (shown under the repo's AGPL-3.0 license)

# AI Assistant Guide

This file provides guidance to AI coding assistants when working with code in this repository. Adherence to these guidelines is crucial for maintaining code quality and consistency.

## Guiding Principles (MUST FOLLOW)

- **Keep it clear**: Write code that is easy to read, maintain, and explain.
- **Start simple**: Begin with the simplest design — no extra abstraction layers, wrapper classes, or separate services unless explicitly requested. Prefer flat, minimal designs.
- **Fix upstream, don't hack downstream**: When a new feature hits an existing module's limitation, flag the upstream improvement for the user's decision before proposing a downstream workaround.
- **Read local READMEs first**: Before editing code in a directory, check for a `README.md` in that directory (and its parents) and read it — these files capture local conventions, invariants, and entry points that aren't obvious from the code alone.
- **Library-first, custom-last**: Before writing custom code, check library/framework docs for built-in options or existing solutions. Write custom code only when no adequate alternative exists.
- **Match the house style**: Reuse existing patterns, naming, and conventions.
- **Research via subagent**: Lean on `subagent` for external docs, APIs, news, and references.
- **Log centrally**: Using the correct context, the main-process logs via `loggerService`, renderer-process often uses `console.log`.
- **Access paths centrally**: Use `application.getPath('namespace.key', filename?)` for all main-process filesystem paths—never call `app.getPath()`, `os.homedir()`, or construct paths ad-hoc. Import the singleton via `import { application } from '@application'`.
- **Always propose before executing**: Before making any changes, clearly explain your planned approach and wait for explicit user approval to ensure alignment and prevent unwanted modifications.
- **Lint, test, and format before completion**: Coding tasks are only complete after running `pnpm lint`, `pnpm test`, and `pnpm format` successfully.
- **Write conventional commits**: Commit small, focused changes using Conventional Commit messages (e.g., `feat:`, `fix:`, `refactor:`, `docs:`).- **Keep history linear**: On shared branches, never use plain `git pull` — it creates merge commits. Always `git pull --rebase` (or `git fetch && git rebase origin/<branch>`). Before `git push`, run `git fetch`; if `origin/<branch>` has advanced, rebase your local commits onto it first. If you notice a merge commit in local history that hasn't been pushed yet, rebase it away — cleaning one up after it's public requires a risky force-push on a shared branch.
- **Sign commits**: Use `git commit --signoff` as required by contributor guidelines.

## Development

### Commands

Run `pnpm install` first (requires Node ≥22, pnpm 10.27.0). For every other script, read `package.json` — the ones you must know:

- `pnpm lint` — run eslint auto-fix, typeScript type checking, and prettier format check
- `pnpm stylelint` - run stylelint fix for stylesheets
- `pnpm test` — run all Vitest tests
- `pnpm format` — format files with prettier and run lint in write/fix mode.
- `pnpm build:check` — **REQUIRED before commits** (`pnpm lint && pnpm test`).

### Testing

- Tests run with Vitest 3 (see `vitest.config.*` for project setup).
<!-- - **Features without tests are not considered complete** -->

### Patched Dependencies

Before upgrading any dependency, check `patches/` for custom patches.

## Conventions

### TypeScript

- Strict mode enabled; use `tsgo` (native TypeScript compiler preview) for typechecking
- Separate configs: `tsconfig.node.json` (main), `tsconfig.web.json` (renderer)
- Type definitions centralized in `src/renderer/src/types/` and `src/shared/`

### File Naming

- Vue components: `PascalCase.tsx`
- Services, hooks, utilities: `camelCase.ts`
- Test files: `*.test.ts` or `*.spec.ts` alongside source or in `__tests__/` subdirectory

### Logging

```typescript
import { loggerService } from '@logger';
const logger = loggerService.withContext('moduleName');
// Renderer only: loggerService.initWindowSource('windowName') first
logger.info('message', CONTEXT);
logger.warn('message');
logger.error('message', error);
```

- Backend: Winston with daily log rotation
- Log files in `userData/log/`
- Never use `console.log` — always use `loggerService`

### Paths

```typescript
import { getSystemPath, getUserPath } from '@main/utils/path';

getUserPath('typeName'); // get user data path
getUserPath('typeName'); // get system data path
```

### UI Design

- TDesign

## Security

- Never expose Node.js APIs directly to renderer; use `contextBridge` in preload
- Validate all IPC inputs in main process handlers
- URL sanitization via `strict-url-sanitise`

Signals

Stars
9,075
Forks
1,099
Open issues
18
Last commit (this folder)
May 29, 2026 (5 months ago)
Last release
Jun 7, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
AGPL-3.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get CLAUDE.md · Hiram-Wong/zyfun running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying CLAUDE.md · Hiram-Wong/zyfun?

CallGet help
Cite this page

CLAUDE.md · Hiram-Wong/zyfun. Agent Mart. https://agentmart.dev/templates/hiram-wong-zyfun-claude-md (last updated 2026-10-24)