AiderDesk is an open-source desktop platform that coordinates AI-assisted software development around the Aider coding tool, letting engineers inspect and control proposed changes. It is for professional developers who want AI help while retaining their existing editor, terminal, and Git workflow. Catalogue add-ons extend its controlled development workflow.
Borrowing it
Nothing to install: this file belongs to hotovo/aider-desk. 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/hotovo/aider-desk/main/AGENTS.mdgit clone --depth 1 https://github.com/hotovo/aider-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/hotovo/aider-desk/agents-md)<a href="https://agentmods.dev/instructions/hotovo/aider-desk/agents-md"><img src="https://agentmods.dev/badge/instructions/hotovo/aider-desk/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 5.1 | $0.01725 | $0.01725 |
| Opus 5 | $0.00863 | $0.00863 |
| Sonnet 5 | $0.00345 | $0.00345 |
| Haiku 4.5 | $0.00172 | $0.00172 |
Grade A, and why
aider-desk 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 8d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AiderDesk when working with code in this repository.
Common Commands
Development
npm install- Install dependenciesnpm run dev- Run in development mode with hot reloadnpm run dev:no-hmr- Run in development mode without hot module replacement
Type Checking
npm run typecheck- Run all TypeScript type checksnpm run typecheck:node- Type check main process files (tsconfig.node.json)npm run typecheck:web- Type check renderer process files (tsconfig.web.json)
Linting and Formatting
eslint --fix- Run ESLint with auto-fix and auto-format on specified file(s)
Testing
npm run test- Run all tests (main + renderer)npm run test:node- Run main, preload, and common process testsnpm run test:web- Run renderer process tests (React components)npm run test:watch- Run tests in watch mode for developmentnpm run test:coverage- Generate coverage reportsnpm run test:ui- Open interactive test UI
Note for Agents: When running 'npm run test' script via power---bash, always append -- --no-color to the command (e.g., npm run test:node -- --no-color) to ensure clean, parseable output without ANSI escape codes. Other scripts can be run without this.
Building
npm run build- Full build (includes type checking)npm run build:win- Build Windows executablenpm run build:mac- Build macOS executablenpm run build:linux- Build Linux executablenpm run build:unpack- Build without packaging
Manual Type Checking (for verification)
tsc --noEmit -p tsconfig.node.json- Check main process filestsc --noEmit -p tsconfig.web.json- Check renderer process files
Dependency Management
- All dependency versions in root
package.json,packages/app/package.json, andpackages/extensions/package.jsonare pinned to exact versions (no^/~ranges). npm stripspackage-lock.jsonfrom published tarballs, so any range would float at install time for consumers. packages/app/scripts/generate-package.mjscopies versions verbatim from rootpackage.jsoninto the published@aiderdesk/aiderdeskpackage — pinning root propagates to the published package on the next build.- To bump a version, change the exact pin (or use the
update-ai-sdk-dependencies.ymlworkflow, which writes exact pins) and runnpm installto sync the lockfile. Never reintroduce^/~ranges. - Exception: the ranged entries under
overrides(@tootallnate/once,jsondiffpatch) are intentional — neither package exists in the lockfile, so there is no resolved version to pin. packages/extensions/package.json(also published,@aiderdesk/extensions) is pinned the same way, except itspeerDependencies(zod) which stays a range — peers declare consumer compatibility and install nothing. Its resolved versions live in the root lockfile: prefer the nestedpackages/extensions/node_modules/<name>resolution when it differs from the hoisted one (e.g.chalk,commander,execa,orahave different hoisted majors at root).- Remaining workspace packages (
packages/common,packages/mcp-server,packages/tree-sitter-utils) are also published and still use ranges; they are not covered by this policy yet.
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.
- 8d ago First seen · 137 lines · 1,725 tokens per session scan A ac4d57dcd2bf
aider-desk AGENTS.md is an instructions file published in the GitHub repository hotovo/aider-desk (1,417 stars, last pushed today), licensed Apache-2.0. It adds 1,725 tokens to every session, about $0.0086 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
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 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).
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.
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.
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).
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.