Borrowing it
Nothing to install: this file belongs to patrickjaja/claude-desktop-extra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/patrickjaja/claude-desktop-extra/master/AGENTS.mdgit clone --depth 1 https://github.com/patrickjaja/claude-desktop-extraWrote 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/patrickjaja/claude-desktop-extra/agents-md)<a href="https://agentmods.dev/instructions/patrickjaja/claude-desktop-extra/agents-md"><img src="https://agentmods.dev/badge/instructions/patrickjaja/claude-desktop-extra/agents-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.
<a href="https://agentmods.dev/instructions/patrickjaja/claude-desktop-extra/agents-md"><img src="https://agentmods.dev/badge/instructions/patrickjaja/claude-desktop-extra/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.07051 | $0.07051 |
| Opus 5.5 | $0.02820 | $0.02820 |
| Sonnet 5.5 | $0.01410 | $0.01410 |
| Haiku 4.5 | $0.00705 | $0.00705 |
Grade B, and why
claude-desktop-extra AGENTS.md scanned grade B with 3 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 yesterday.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
# Install RPM: sudo dnf install /media/sf_shared/claude-desktop-extra-*.x86_64.rpm Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `baseline/CUSTOM_MODELS_ANCHORS.md` | Custom models: the build-time anchors of `add_feature_custom_models.nim` (sub-patches B, C, D and C's transport-shape asserts), and the run-time assumptions no build can check - th Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
**Rule when adding a patch:** if it writes to a fixed user-level path, prefer `app.getPath("userData")` (auto-isolates) over `os.homedir()+"/.config/Claude"`. If it opens a Unix socket or pipe owned by the Electron proce How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Project Guidelines
Project Overview
This project repackages Anthropic's official Claude Desktop Linux .deb for the distros Anthropic does not ship (Arch via our own pacman repo, Fedora/RHEL via RPM, NixOS, AppImage, plus our own Debian/Ubuntu .deb). It applies JavaScript patches to the official build's app.asar to add Linux-only value-adds (Computer Use, custom themes, multi-profile, Quick Entry) and Linux fixes.
The official .deb (apt repo https://downloads.claude.ai/claude-desktop/apt) bundles its own Electron (44.9.0 as of v3.1623.0; authoritative source: the deb tree's usr/lib/claude-desktop/version file) and a native Cowork VM backend. We download it, verify GPG + SHA256, extract it, patch its app.asar, and repackage. We do not pin Electron or rebuild node-pty (both ship pre-built in the .deb).
Layout invariant (2026-07-13): every package ships the .deb's usr/lib/claude-desktop/ tree verbatim (binary renamed claude-desktop -> claude; patched resources/app.asar exe-adjacent; our CU bridges added to resources/). Electron auto-loads the adjacent asar - the official build's OnlyLoadAppFromAsar + EnableEmbeddedAsarIntegrityValidation fuses are on (integrity is not enforced on Linux, which is why a patched asar boots). The launcher passes NO asar on the command line, so process.resourcesPath and app.isPackaged behave exactly as on the stock Anthropic .deb. Never add a patch that redirects resource paths; put bundled files at their upstream resources/ position instead. On NixOS the nixpkgs Electron dist is merged with our resources/ into one directory to preserve the same adjacency.
- Target platform: Linux only (X11, Wayland, XWayland). No macOS/Windows code.
One exception: custom models (
js/custom_models_main.js, and its CLI preloadjs/custom_models_preload.js) and the Extra settings page (js/extra_settings_main.js,js/extra_settings_page.js) also load onwin32, so the downstream Windows build (stratosjl/claude-desktop-extra) carries them unedited. Keep those win32 branches behind their platform checks and their tests green; they must never change Linux behavior. Do not add Windows code anywhere else. - Architectures: x86_64 (primary) and aarch64.
- glibc floor: 2.34 (RHEL 9 / Ubuntu 22.04). Debian 11 is not supported. If upstream's
claude-native-binding.nodeasks for a glibc above 2.34 through weak symbols only (v2.19675.1 did, for GLIBC_2.39; v2.26454.0 tops out at 2.34),scripts/fix-native-glibc-floor.pymarks those version-needs weak at build time; a strong symbol above the floor fails the build, and CI asserts the result. - Native binaries we ship (the four Computer Use bridges) build for x86_64 AND aarch64, each with a stated glibc floor or as static musl; CI verifies with
objdump -T | grep GLIBC_. A new native binary picks the floor of its minimum viable distro. - RPM caveat: the spec excludes the bundled tree from rpm's automatic ELF dependency generator (
__requires_exclude_frominpackaging/rpm/claude-desktop-extra.spec); without it the bridges' glibc-2.39 symbols block install on RHEL 9. CI's rockylinux:9 install test guards this.
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.
- yesterday Changed · +21 lines · +602 tokens per session 142d3f5165c5
- yesterday Changed · +1 lines · +35 tokens per session 930b35ad587d
- 8d ago Changed 3d4fd9ef7b49
- 9d ago Changed · +2 tokens per session 54b279ba1da3
- 14d ago Changed · +1 lines · +126 tokens per session a0cca523dbfd
- 15d ago Changed 2ce21bc94f80
- 16d ago Changed b868c378b0ad
- 20d ago Changed · +22 lines · +638 tokens per session fb69192046ff
- 21d ago Changed 70df91fe55e1
- 22d ago First seen · 233 lines · 5,648 tokens per session scan B 6e7c7f550075
claude-desktop-extra AGENTS.md is an instructions file published in the GitHub repository patrickjaja/claude-desktop-extra (726 stars, last pushed yesterday), licensed MIT. It adds 7,051 tokens to every session, about $0.0282 per session on Opus 5.5. A static security scan graded it B with 3 findings (asks for root, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
claude-desktop-extra AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-desktop-extra AGENTS.mdpatrickjaja/claude-desktop-extra | Instructions file | 726 | yesterday | MIT | B | 7,051 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | 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 |