What is viwo CLAUDE.md?

A repository instruction file for Claude Code, documenting how to install dependencies, check types, test, format, lint, build, manage database changes, run the CLI, and release the project.

Use it to find the project’s development, testing, database, command-line, and release procedures.

It gives the coding agent and developers a shared reference for the commands used to work on this codebase.

How OverseedAI/viwo configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to OverseedAI/viwo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/OverseedAI/viwo/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/OverseedAI/viwo

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/overseedai/viwo/claude-md/github.svg)](https://agentmods.dev/instructions/overseedai/viwo/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/overseedai/viwo/claude-md"><img src="https://agentmods.dev/badge/instructions/overseedai/viwo/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/overseedai/viwo/claude-md"><img src="https://agentmods.dev/badge/instructions/overseedai/viwo/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 6,576 This file is loaded in full into every session.

When invoked 6,576 The same file — it is already loaded in full.

Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.06576	$0.06576
Opus 5.5	$0.02630	$0.02630
Sonnet 5.5	$0.01315	$0.01315
Haiku 4.5	$0.00658	$0.00658

Measured 4d ago against content hash 0942750cbb49, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

viwo CLAUDE.md scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

RUN curl -fsSL https://bun.sh/install | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

RUN curl -fsSL https://bun.sh/install | bash

CLAUDE.md · 530 lines

How it starts

The opening of the file, as written. The whole thing — 530 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Build and Development Commands

# Install dependencies
bun install

# Type checking
bun run typecheck              # All packages
cd packages/core && bun run typecheck  # Core only

# Testing
cd packages/core && bun test   # Run all tests
bun test <test-file>.test.ts   # Run specific test

# Code quality
bun run format                 # Format code
bun run format:check           # Check formatting
bun run lint                   # Lint code

# Build for production
bun run build                  # All packages

# Database (schema changes)
cd packages/core
bun run db:generate            # Step 1: Generate Drizzle SQL migrations from schema files
bun run db:migrate             # Step 2: Convert SQL migrations to JS migration format in src/migrations/index.ts

# Run CLI during development
bun packages/cli/src/cli.ts --help  # Direct source execution
viwo --help                         # If globally linked

# Release
bun run release 0.1.2          # Bump version, commit, and tag

Release Process

To release a new version:

Bump version and create tag:
```
bun run release <version>
# Example: bun run release 0.1.2
```
This will:
- Update version in packages/core/package.json and packages/cli/package.json
- Update CLAUDE_CODE_IMAGE in packages/core/src/managers/docker-manager.ts to overseedai/viwo-claude-code:<version>
- Create a git commit: "chore: bump version to X.Y.Z"
- Create a git tag: vX.Y.Z

Push to trigger release workflow:

git push origin main
git push origin vX.Y.Z

GitHub Actions workflows triggered on tag push matching v*:
- .github/workflows/release.yml — Builds CLI binaries for all platforms (Linux, macOS, Windows) using native GitHub runners, creates checksums, and publishes a GitHub release with binaries attached. Pins Bun to a known-good version.
- .github/workflows/docker-publish.yml — Builds and publishes the Claude Code runtime image (packages/agents/claude-code/Dockerfile) to Docker Hub as overseedai/viwo-claude-code:<version> and overseedai/viwo-claude-code:latest. Multi-arch (linux/amd64, linux/arm64). Requires DOCKERHUB_USERNAME and DOCKERHUB_TOKEN repo secrets.

Read the full file on GitHub · 530 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

4d ago Changed · +2 lines · +80 tokens per session 0942750cbb49
2mo ago First seen · 528 lines · 6,496 tokens per session scan C a13c34284ed0

Subscribe to this mod's changes

viwo CLAUDE.md is an instructions file published in the GitHub repository OverseedAI/viwo (65 stars, last pushed 4d ago), licensed MIT. It adds 6,576 tokens to every session, about $0.0263 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

viwo CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
viwo CLAUDE.mdOverseedAI/viwo	Instructions file	65	4d ago	MIT	C	6,576	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

viwo: Instructions file for Claude Code