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/outlinefoundation/outline-apps/agents-mdgit clone --depth 1 https://github.com/OutlineFoundation/outline-appsWrote 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/outlinefoundation/outline-apps/agents-md)<a href="https://agentmods.dev/instructions/outlinefoundation/outline-apps/agents-md"><img src="https://agentmods.dev/badge/instructions/outlinefoundation/outline-apps/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 | $0.00797 | $0.00797 |
| Opus 5 | $0.00398 | $0.00398 |
| Sonnet 5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
outline-apps 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.
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.
Welcome to the Outline Monorepo!
This document provides a guide for AI and human agents working with the Outline codebase.
Repository Structure
The Outline monorepo is organized into three main components:
/client: The Outline Client application, available on all major platforms. Seeclient/AGENTS.md./server_manager: A graphical application to create and manage Outline Servers. Seeserver_manager/AGENTS.md./infrastructure: The build system and shared TypeScript utilities. Seeinfrastructure/AGENTS.md.
The npm run action Command
The primary entry point for all development tasks is npm run action <path>, which resolves to .action.sh or .action.mjs files in the repo. Run npm run action list to see all available actions. Pass flags after --:
npm run action client/src/cordova/setup macos -- --buildMode=release
Common Actions
npm run action list: Lists all available actions.npm run action client/web/start: Starts a dev server for the shared web UI.npm run action server_manager/www/start: Starts a dev server for the Manager UI.npm run action <component>/test: Runs tests (e.g.npm run action client/web/test).npm run action <component>/build: Builds a component (e.g.npm run action client/electron/build linux -- --arch=x64).
Other useful commands
npm run reset: Clean and reinstall all dependencies (fixes most build issues).npm run storybook: Launch the Storybook UI component explorer.npm run lint:gts: Lint TypeScript (pass filepaths on macOS; works on all files on Linux).
Code Style
- TypeScript: Follows Google's TypeScript style, enforced by
gts. Runnpm run lint:gtsto check andnpm run format:allto auto-fix (Linux only for whole codebase; pass specific filepaths on macOS). - Go: Follows standard Go style. Use
gofmtandgo vet.
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 · 797 tokens per session scan A 68a558ae2d02
outline-apps AGENTS.md is an instructions file published in the GitHub repository OutlineFoundation/outline-apps (9,238 stars, last pushed yesterday), licensed Apache-2.0. It adds 797 tokens to every session, about $0.0040 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
itsyconnect-macos CLAUDE.md
Instructions for nickustinov/itsyconnect-macos, covering itsyconnect – llm build guide, required reading, project rules, core principles and routing and request interception.
unity-cross-platform-local-build-orchestrator AGENTS.md
Instructions for sinanata/unity-cross-platform-local-build-orchestrator, covering agents.md, what this project is, golden rules (do not violate), use it and interface.
unity-cross-platform-local-build-orchestrator copilot-instructions.md
Instructions for sinanata/unity-cross-platform-local-build-orchestrator: This repository follows the cross-tool AGENTS.md standard. Read /AGENTS.md for the full guide: the script/CLI interface, the config workflow, and the operating rules.
FluidAudio copilot-instructions.md
Copilot instructions for FluidInference/FluidAudio, covering fluidaudio - agent development guide, build & test commands, architecture, critical rules and code style (swift-format config).
speech-swift AGENTS.md
AGENTS.md instructions for soniqo/speech-swift, covering agent instructions, communication style, workflow, running tests and benchmarks — sequential and memory-aware and git conventions.
maui-labs AGENTS.md
AGENTS.md instructions for dotnet/maui-labs, covering agent instructions, repository overview, products, technology stack and building.