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/gecko51/link-desk/claude-mdgit clone --depth 1 https://github.com/Gecko51/link-deskWrote 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/gecko51/link-desk/claude-md)<a href="https://agentmods.dev/instructions/gecko51/link-desk/claude-md"><img src="https://agentmods.dev/badge/instructions/gecko51/link-desk/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 5.1 | $0.01748 | $0.01748 |
| Opus 5 | $0.00874 | $0.00874 |
| Sonnet 5 | $0.00350 | $0.00350 |
| Haiku 4.5 | $0.00175 | $0.00175 |
Grade A, and why
link-desk 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 5d 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 — 92 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.
Projet
LinkDesk — application de contrôle à distance type TeamViewer. Stack : Tauri 2.x + React 18 / TypeScript strict + Rust + WebRTC + Node.js signaling.
Monorepo npm workspaces :
desktop-app/— client Tauri (host + controller, frontend React + backend Rust natif)signaling-server/— serveur WebSocket de signaling (Fastify + ws, opérationnel depuis Phase 2)
À lire avant de toucher au code
PRD.md— spec produit complète : 5 phases (v0.1 → v1.0), user stories, data model, commandes Tauri, messages WS/data-channel, contraintes perf/sécu.STRUCTURE.md— arborescence cible du monorepo. Respecter les chemins et le nommage (kebab-case.tsxcôté frontend,snake_case.rscôté Rust).DEV-RULES.md— règles de code, UI/UX, sécurité, git, debug. Non négociable.docs/superpowers/plans/— plan d'implémentation détaillé par phase (Phases 1-3 complètes).
Conventions qui dérogent aux préférences globales
- Commentaires de code en anglais (DEV-RULES §1 — convention internationale). Seuls la prose utilisateur, les READMEs, CHANGELOG et documents restent en français.
- TypeScript strict obligatoire : pas de
any, pas deas unknown as. Props typées systématiquement. Extend des props HTML viaReact.ComponentProps<'button'>. - Rust : pas de
.unwrap()/.expect()en prod, erreurs viathiserror, zéro warningclippytoléré (#![deny(warnings)]en Phase 5). - Zod obligatoire pour valider toute donnée venant de l'extérieur (WS, data channel, commandes Tauri, localStorage). Dette Phase 1 encore ouverte : le wrapper
src/lib/tauri.tsne valide toujours pas les résultats Tauri (commandes actuelles = string simple) — à câbler quand une commande structurée arrivera (Phase 3/4). - Schémas Zod dupliqués entre
signaling-server/src/websocket/schemas.tsetdesktop-app/src/features/signaling/message-schemas.tsdepuis Phase 2 (duplication contrôlée). À consolider en package partagé en Phase 5 — évite de coupler le bundler Tauri au workspace serveur. - Context7 MCP : requis avant de coder une API de librairie (tauri, tauri-plugin-stronghold, react-router-dom, fastify, ws, zod, shadcn). Ne jamais coder une API de mémoire sans check.
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.
- 5d ago First seen · 92 lines · 1,748 tokens per session scan A 44b203a59f4f
link-desk CLAUDE.md is an instructions file published in the GitHub repository Gecko51/link-desk (5 stars, last pushed 4mo ago), licensed MIT. It adds 1,748 tokens to every session, about $0.0087 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.