What is overseer CLAUDE.md?

A project instruction document for Overseer, a desktop app for using local AI coding agents, viewing repositories, chatting with an agent, and working in a terminal.

Use it when developing or reviewing Overseer, especially changes involving agent backends, privacy, performance, or the desktop interface.

It gives contributors the project’s design rules, architecture guidance, commands, and review checklist in one place.

How marcinbunsch/overseer configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to marcinbunsch/overseer. 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/marcinbunsch/overseer/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/marcinbunsch/overseer

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/marcinbunsch/overseer/claude-md/github.svg)](https://agentmods.dev/instructions/marcinbunsch/overseer/claude-md)

Your own site

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

Per session 1,615 This file is loaded in full into every session.

When invoked 1,615 The same file — it is already loaded in full.

Security scan A 0 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	$0.01615	$0.01615
Opus 5.5	$0.00646	$0.00646
Sonnet 5.5	$0.00323	$0.00323
Haiku 4.5	$0.00161	$0.00161

Measured 2mo ago against content hash 8253263ea529, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

overseer CLAUDE.md scanned grade A with 0 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 2mo 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 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.

What is Overseer

Overseer is a desktop GUI frontend for AI coding agents (Claude Code, Codex, OpenCode). Built with Tauri v2, it provides a three-pane interface: repository/workspace management (left), chat with Claude (middle), and an integrated terminal with changed-files view (right).

For full architecture, component map, data models, and feature documentation, see docs/OVERSEER.md.

Design Principles

These principles must guide all code changes:

Private: No telemetry, no API keys, no cloud integrations. Overseer talks to CLI tools the user installs locally. Never add analytics, tracking, or external service calls.
Performant: No idle polling, no background refreshes, no wasted cycles. Everything is event-driven and reactive. Minimize resource usage — don't add timers, intervals, or periodic fetches.
Extensible: The agent abstraction (AgentService interface in services/types.ts) is designed so new agent backends can be added without modifying existing code. Keep this boundary clean.

Development Commands

pnpm dev          # Full Tauri dev mode (frontend + Rust backend with hot reload)
pnpm build        # Production build (runs tsc + vite build + tauri build)
pnpm vite-dev     # Frontend-only dev server (no Tauri shell)
pnpm vite-build   # TypeScript check + Vite production build
pnpm test         # Run tests (vitest)
pnpm test:watch   # Run tests in watch mode
pnpm checks       # All checks: format + lint + typecheck + rustcheck
pnpm checks:ui    # UI-only checks: format + lint + typecheck
pnpm lint         # ESLint
pnpm format       # Prettier (write)
pnpm format:check # Prettier (check only)

Package manager is pnpm (v10.17.1).

Pre-commit Checklist

Always run before committing:

pnpm checks       # Full check (UI + Rust)
pnpm checks:ui    # UI-only changes (no Rust check)

Read the full file on GitHub · 115 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.

2mo ago First seen · 115 lines · 1,615 tokens per session scan A 8253263ea529

Subscribe to this mod's changes

overseer CLAUDE.md is an instructions file published in the GitHub repository marcinbunsch/overseer (11 stars, last pushed 1mo ago), licensed MIT. It adds 1,615 tokens to every session, about $0.0065 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

overseer CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
overseer CLAUDE.mdmarcinbunsch/overseer	Instructions file	11	1mo ago	MIT	A	1,615	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

overseer: Instructions file for Claude Code