agent-desktop CLAUDE.md

agent-desktop CLAUDE.md is an instructions file for coding agents from BaLaurent/agent-desktop. It costs 5,749 tokens per session, scanned A, original, AGPL-3.0.

Project instructions for BaLaurent/agent-desktop, covering how its codebase should be built, run, structured, and changed.

In plain words
What is it for?
Following build and run steps, applying architecture decisions, respecting conventions, and handling instruction ordering.
Why use it?
They give an agent the project's local rules so its changes follow the intended architecture and conventions.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/balaurent/agent-desktop/claude-md
Clone the repo
git clone --depth 1 https://github.com/BaLaurent/agent-desktop

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.

agentmods badge for agent-desktop CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/balaurent/agent-desktop/claude-md.svg)](https://agentmods.dev/instructions/balaurent/agent-desktop/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/balaurent/agent-desktop/claude-md"><img src="https://agentmods.dev/badge/instructions/balaurent/agent-desktop/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,749 This file is loaded in full into every session.
When invoked 5,749 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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.

ModelPer sessionOnce invoked
Fable 5 $0.05749 $0.05749
Opus 5 $0.02874 $0.02874
Sonnet 5 $0.01150 $0.01150
Haiku 4.5 $0.00575 $0.00575

Measured 4d ago against content hash c295e1cb9948, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-desktop 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 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.

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 · 164 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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.

  1. 4d ago First seen · 164 lines · 5,749 tokens per session scan A c295e1cb9948

Subscribe to this mod's changes

agent-desktop CLAUDE.md is an instructions file published in the GitHub repository BaLaurent/agent-desktop (53 stars, last pushed 3d ago), licensed AGPL-3.0. It adds 5,749 tokens to every session, about $0.0287 per session on Opus 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.