Borrowing it
Nothing to install: this file belongs to ObscuritySRL/umbriel. 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/ObscuritySRL/umbriel/main/AGENTS.mdgit clone --depth 1 https://github.com/ObscuritySRL/umbrielWrote 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/obscuritysrl/umbriel/agents-md)<a href="https://agentmods.dev/instructions/obscuritysrl/umbriel/agents-md"><img src="https://agentmods.dev/badge/instructions/obscuritysrl/umbriel/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/obscuritysrl/umbriel/agents-md"><img src="https://agentmods.dev/badge/instructions/obscuritysrl/umbriel/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 | $0.03391 | $0.03391 |
| Opus 5.5 | $0.01356 | $0.01356 |
| Sonnet 5.5 | $0.00678 | $0.00678 |
| Haiku 4.5 | $0.00339 | $0.00339 |
Grade A, and why
umbriel 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 2mo 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
Rules for working in umbriel — Playwright for the Windows desktop, from Bun. A single, zero-native-dependency package that drives and tests native Windows GUIs through the UI Automation accessibility tree (find by name, invoke, type, assert), plus synthetic input, full-screen capture + image matching, native-window introspection (Spy++-style), an LLM computer-use adapter, OCR, and a stdio MCP server. No node-gyp, no prebuilt binaries, no sidecar process. Follow these rules exactly.
umbriel is pure TypeScript over bun:ffi. It does not bind any DLL itself — it consumes the published @bun-win32/* FFI binding packages (core, user32, oleacc, combase, kernel32, gdi32, shell32, shcore, oleaut32, advapi32, dwmapi, d3d11) as ordinary pinned npm dependencies, and composes them into a high-level desktop-automation API. (One exception: a Win32 symbol/DLL that no installed @bun-win32/* binding covers may be hand-rolled here as a last resort — see the FFI Binding Rules — but every such case is logged in TODO.md for the owner to upstream into bun-win32.)
umbriel was extracted from the
bun-win32monorepo (formerly@bun-win32/uia+bun-uia) into its own standalone repo and unscoped npm package. The FFI layer it stands on still lives in@bun-win32/*; only the product is standalone.
Core Principles
- Plan before implementing. Read and understand the problem, the existing code, and the surrounding context before writing anything. Do not guess at what code does — read it.
- No fabrication — verify every claim. This drives a real OS through real accessibility and input APIs. Never guess a signature, HRESULT, pattern id, or nullability. Verify against the Microsoft Learn docs page and the upstream
@bun-win32/*binding. Incorrect FFI usage segfaults; incorrect information is worse than none. If you do not know, say so. - Minimal, surgical diffs. Change only what the task requires. Do not "clean up," reformat, or refactor code you were not asked to touch.
- No premature abstraction. No helpers, wrappers, or utilities unless explicitly requested. Keep the public facade thin.
- Verify at every step. After every meaningful change, prove it works: run the file (
bun run …), type-check (bunx tsc --noEmit), and run the relevant example/test. Do not pile changes on a broken state. - Safety is load-bearing. The MCP server exposes this machine to an LLM. Capability profiles, credential redaction, and the cursor-free input paths are security features — never weaken them to make a demo pass.
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.
- 2mo ago First seen · 172 lines · 3,391 tokens per session scan A 12773f30230c
umbriel AGENTS.md is an instructions file published in the GitHub repository ObscuritySRL/umbriel (3 stars, last pushed 2mo ago), licensed MIT. It adds 3,391 tokens to every session, about $0.0136 per session on Opus 5.5. 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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.