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/cdesktop-ai/cdesktop/agents-mdgit clone --depth 1 https://github.com/cdesktop-ai/cdesktopWrote 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/cdesktop-ai/cdesktop/agents-md)<a href="https://agentmods.dev/instructions/cdesktop-ai/cdesktop/agents-md"><img src="https://agentmods.dev/badge/instructions/cdesktop-ai/cdesktop/agents-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 | $0.01005 | $0.01005 |
| Opus 5 | $0.00502 | $0.00502 |
| Sonnet 5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
cdesktop AGENTS.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.
This is a copy
100% identical to vibe-kanban AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
crates/: Rust workspace crates —server(API + bins),db(SQLx models/migrations),executors,services,utils,git(Git operations),api-types(shared API types for local + remote),review(PR review tool),deployment,local-deployment,remote.packages/local-web/: Local React + TypeScript app entrypoint (Vite, Tailwind). Shell source inpackages/local-web/src.packages/remote-web/: Remote deployment frontend entrypoint.packages/web-core/: Shared React + TypeScript frontend library used by local + remote web (packages/web-core/src).shared/: Generated TypeScript types (shared/types.ts,shared/remote-types.ts) and agent tool schemas (shared/schemas/). Do not edit generated files directly.assets/,dev_assets_seed/,dev_assets/: Packaged and local dev assets.npx-cli/: Files published to the npm CLI package.scripts/: Dev helpers (ports, DB preparation).docs/: Documentation files.
Crate-specific guides
crates/remote/AGENTS.md— Remote server architecture, ElectricSQL integration, mutation patterns, environment variables.docs/AGENTS.md— Mintlify documentation writing guidelines and component reference.packages/local-web/AGENTS.md— Web app design system styling guidelines.
Managing Shared Types Between Rust and TypeScript
ts-rs allows you to derive TypeScript types from Rust structs/enums. By annotating your Rust types with #[derive(TS)] and related macros, ts-rs will generate .ts declaration files for those types.
When making changes to the types, you can regenerate them using pnpm run generate-types
Do not manually edit shared/types.ts, instead edit crates/server/src/bin/generate_types.rs
For remote/cloud types, regenerate using pnpm run remote:generate-types
Do not manually edit shared/remote-types.ts, instead edit crates/remote/src/bin/remote-generate-types.rs (see crates/remote/AGENTS.md for details).
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 · 59 lines · 1,005 tokens per session scan A c82e8bb68b45
cdesktop AGENTS.md is an instructions file published in the GitHub repository cdesktop-ai/cdesktop (108 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,005 tokens to every session, about $0.0050 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to vibe-kanban AGENTS.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
alego AGENTS.md
Instructions for singula-ai/alego, covering agents.md, pre-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.
Atomic-Chat AGENTS.md
AGENTS.md instructions for AtomicBot-ai/Atomic-Chat, covering agents.md — atomic chat, 1. what this is, 2. repository map, 3. backends — the part that is easy to get wrong and 4. naming: what you may not rename.
U-Pool CLAUDE.md
Claude Code instructions for U-C4N/U-Pool, covering working in this repository, never run a write path against the real home, reading live config is fine, tests and ownership is the load-bearing idea.
SkillsAllYouNeed CLAUDE.md
Claude Code instructions for kishormorol/SkillsAllYouNeed: Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
alego CLAUDE.md
Instructions for singula-ai/alego, a project described as: Build AI Agents like playing LEGOs. Everything is a Plugin.
oc-go-cc-optim CLAUDE.md
Claude Code instructions for newmancai/oc-go-cc-optim, covering claude.md, commands, architecture and key files.