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.
npx agentmods add instructions/lahfir/agent-desktop/claude-mdgit clone --depth 1 https://github.com/lahfir/agent-desktopWrote 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.
[](https://agentmods.dev/instructions/lahfir/agent-desktop/claude-md)<a href="https://agentmods.dev/instructions/lahfir/agent-desktop/claude-md"><img src="https://agentmods.dev/badge/instructions/lahfir/agent-desktop/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.05828 | $0.05828 |
| Opus 5 | $0.02914 | $0.02914 |
| Sonnet 5 | $0.01166 | $0.01166 |
| Haiku 4.5 | $0.00583 | $0.00583 |
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.
How it starts
The opening of the file, as written. The whole thing — 425 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.
Common Commands
cargo build # Debug build
cargo build --release # Release build (<15MB target)
cargo test --workspace # Run every test (lib, binary, and integration targets)
cargo test --lib --workspace # Library unit tests only; SKIPS the agent-desktop binary crate
cargo test -p agent-desktop # Binary crate tests (CLI contract, dispatch, batch, policy)
cargo test --lib -p agent-desktop-core # Test core crate only
cargo test --lib -p agent-desktop-macos # Test macOS crate only
cargo test test_name # Run a single test by name
cargo check -p agent-desktop-core --all-targets --target x86_64-pc-windows-msvc # Core must cross-compile
cargo check -p agent-desktop-core --all-targets --target x86_64-unknown-linux-gnu
cargo clippy --all-targets -- -D warnings # Lint (must pass, zero warnings)
cargo fmt --all -- --check # Format check
cargo fmt --all # Auto-format
cargo tree -p agent-desktop-core # Verify no platform crate leaks (CI enforces)
bash tests/e2e/run.sh # E2E: real binary vs fixture app, verify by observation (needs --release + AX permission)
bash scripts/perf-baseline-compare.sh # Perf A/B vs merge-base -> report.html (add --apps "Slack,Google Chrome" for Electron coverage)
Run the binary: ./target/release/agent-desktop snapshot --app Finder -i
The E2E harness drives the release binary against a real SwiftUI/AppKit fixture and asserts every effect by independent observation (never the command's own ok:true), covering every ref action in both headless and --headed mode. See tests/e2e/README.md.
Pre-commit Hook
The repo ships a pre-commit hook at .githooks/pre-commit that runs cargo fmt --check, cargo clippy --all-targets -- -D warnings, and cargo test --lib --workspace against staged Rust changes. Wire it up once after cloning:
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 First seen · 425 lines · 5,828 tokens per session scan A 85bf9e410ace
agent-desktop CLAUDE.md is an instructions file published in the GitHub repository lahfir/agent-desktop (1,034 stars, last pushed today), licensed Apache-2.0. It adds 5,828 tokens to every session, about $0.0291 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.
Other instructions, from other repositories
kwin-mcp CLAUDE.md
Instructions for isac322/kwin-mcp, covering claude code working guidelines, project overview, toolchain, common commands and code style.
mcp-server-uiautomation copilot-instructions.md
Copilot instructions for trsdn/mcp-server-uiautomation, covering github copilot instructions - uiautomationmcp, project focus, read first, core rules and quick validation.
mcp-server-uiautomation testing-strategy.instructions.md
Instructions for trsdn/mcp-server-uiautomation: Use the smallest relevant verification step.
agent-computer-use-mcp AGENTS.md
AGENTS.md instructions for astraclawteam/agent-computer-use-mcp, covering agent worker rules, read order, repository purpose, project structure and branch and pr rules.
oculos AGENTS.md
Instructions for huseyinstif/oculos, covering oculos — ai agent instructions, core workflow, discovery, list all windows and search for elements (preferred — fast).
mcp-server-uiautomation architecture-patterns.instructions.md
Instructions for trsdn/mcp-server-uiautomation, a project described as: Windows UI Automation toolkit with CLI, MCP server, and VS Code extension.