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/robdel12/orbitdock/agents-mdgit clone --depth 1 https://github.com/Robdel12/OrbitDockWhat 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 | $0.00935 | $0.00935 |
| Opus 5 | $0.00467 | $0.00467 |
| Sonnet 5 | $0.00187 | $0.00187 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
OrbitDock 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 2d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
AGENTS.md is the front door, not the handbook.
Start here, then jump to the right doc.
Read This First
If you're making code changes, these are the docs that matter most:
- docs/GETTING_STARTED.md — project setup, build commands, testing, and day-to-day workflow
- docs/ARCHITECTURE.md — client patterns, server state architecture, and guardrails
- docs/OPERATIONS.md — server deployment, persistence, debugging, and troubleshooting
Short Version
OrbitDock has two main parts:
OrbitDockNative/OrbitDock/— SwiftUI app for macOS and iOSorbitdock-server/— Rust server, CLI, persistence, and provider integrations
The repo rules are simple:
- keep durable business truth on the server
- apply authoritative
POST/PATCH/PUTresponses to local state immediately, then let subscriptions reconcile - use
make rust-*targets instead of plaincargo - keep shared Make config in the root
Makefileand target families inmake/*.mk - keep SQLite ownership in the Rust server
- prefer focused docs in
docs/over growing this file again
Native App Workflow
For Swift app work, prefer the newer plugin skills and MCP tools over ad hoc shell workflows.
- use the
Build iOS Appsplugin for iOS build, simulator, UI inspection, screenshots, logs, and debugger flows - use the
Build macOS Appsplugin for macOS build, run, test, debug, telemetry, and packaging flows - when the task clearly matches one of the native skills, load it first instead of reaching straight for raw
xcodebuild - prefer
build-ios-apps:ios-debugger-agentfor simulator runs and interactive iOS debugging - prefer
build-macos-apps:build-run-debugfor local macOS build and launch work, andbuild-macos-apps:test-triagewhen macOS tests fail - prefer the
mcp__xcodebuildmcp__*tool family for simulator control, screenshots, UI snapshots, log capture, and Xcode-backed build/test actions - use shell
xcodebuildorswift buildas a fallback when the MCP/plugin path does not cover the task cleanly
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.
- 2d ago First seen · 76 lines · 935 tokens per session scan A b6db072c0ff1
OrbitDock AGENTS.md is an instructions file published in the GitHub repository Robdel12/OrbitDock (95 stars, last pushed 4mo ago), licensed MIT. It adds 935 tokens to every session, about $0.0047 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
skills-manager CLAUDE.md
Instructions for yibie/skills-manager, covering skills manager - development guide, tui engine: blessed, 核心原则, 参考文档 and 正确的 list 用法.
swift-tui AGENTS.md
Instructions for SwiftTUI/swift-tui, covering agents.md, build & test commands, architecture (one-page summary), development guidelines and code style.
skills-manager AGENTS.md
Instructions for yibie/skills-manager, covering repository agent instructions and ui and interaction work.
here-macos CLAUDE.md
Instructions for koalaauto/here-macos, covering here — ai assistant notes, architecture at a glance, prerequisites, build & run and always pass -quiet from an agent session.
here-macos AGENTS.md
Instructions for koalaauto/here-macos: Canonical project notes — architecture, conventions, gotchas, versioning — live in CLAUDE.md.
pareto-mac AGENTS.md
AGENTS.md instructions for ParetoSecurity/pareto-mac, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.