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/thedartsco/orbit/agents-mdgit clone --depth 1 https://github.com/TheDartsCo/orbitWrote 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/thedartsco/orbit/agents-md)<a href="https://agentmods.dev/instructions/thedartsco/orbit/agents-md"><img src="https://agentmods.dev/badge/instructions/thedartsco/orbit/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 | $0.02041 | $0.02041 |
| Opus 5 | $0.01020 | $0.01020 |
| Sonnet 5 | $0.00408 | $0.00408 |
| Haiku 4.5 | $0.00204 | $0.00204 |
Grade A, and why
orbit 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to WARP (warp.dev) when working with code in this repository.
What is Orbit
Orbit is a Tauri v2 desktop app that aggregates and displays coding agent session transcripts from multiple AI tools (Claude Code, Codex, Cursor, OpenCode). It indexes session files from each tool's local storage into a unified SQLite database, then presents them in a searchable, filterable UI with transcript viewing and session resume capabilities.
Build & Dev Commands
npm run tauri dev— Run the full app in dev mode (starts Vite frontend + Rust backend)npm run dev— Start only the Vite frontend dev server (port 1420)npm run build— TypeScript check + Vite production build (frontend only)npm run tauri build— Full production build (frontend + Rust, produces native binary)cargo build— Build only the Rust backend (run fromsrc-tauri/)cargo test— Run Rust tests (run fromsrc-tauri/)tsc --noEmit— TypeScript type check without emitting
There is no linter, formatter, or test runner configured for the frontend. There are no frontend tests.
Architecture
Two-process Tauri model
The app follows Tauri v2's split architecture:
- Frontend (
src/): React 19 + TypeScript + Tailwind CSS v4 + Vite. Communicates with the backend exclusively viainvoke()from@tauri-apps/api/core. - Backend (
src-tauri/): Rust. Exposes Tauri commands that the frontend calls. Manages all data access, file system scanning, and session parsing.
Backend (Rust) — key modules
adapters/— One adapter per agent tool (Claude, Codex, Cursor, OpenCode). Each implements theAgentAdaptertrait which defines:detect()(is the tool installed?),scan()(find session files on disk),parse_session()(parse a session file into normalizedNormalizedSession),resume_command(), andis_active(). TheAdapterRegistryholds all adapters in a HashMap keyed by string ID.adapters/claude.rs— Filters out Claude-Mem plugin observer sessions by checking if the first user message contains "claude-mem" or "Hello memory agent". These returnErr("Subagent/plugin session, skipping")fromparse_session().indexer/— Orchestrates scanning all adapters, parsing sessions, upserting into SQLite, managing stale session cleanup, and rebuilding the FTS5 index. Uses a size+mtime hash to skip unchanged files. Important:mark_stale_sessions()is called ONCE after ALL adapters finish (not per-adapter), using combined paths from every adapter — otherwise each adapter would delete the previous adapter's sessions.db/—schema.rscreates tables (sessions, messages, attachments) and amessages_ftsFTS5 virtual table.queries.rsprovidesDbQueriesfor all SQL operations. The database lives at~/<platform data dir>/orbit/orbit.dbwith WAL mode enabled.commands.rs— Tauri command handlers (#[tauri::command]). These are the IPC boundary:get_sessions,get_session_messages,search_sessions,get_resume_command,launch_resume,get_active_sessions,reindex_all.watcher.rs— File system watcher using thenotifycrate (kqueue on macOS). Currently defined but not wired into the main app loop.models.rs— Shared data types:Session,Message,Attachment,AgentType,MessageRole,SessionFilters. These are serialized to/from JSON for the frontend via serde.
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 · 82 lines · 2,041 tokens per session scan A dd553ed2c5a5
orbit AGENTS.md is an instructions file published in the GitHub repository TheDartsCo/orbit (10 stars, last pushed 10d ago), licensed MIT. It adds 2,041 tokens to every session, about $0.0102 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 2026-08-31.
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.