What is orbit AGENTS.md?

Repository instructions for Orbit, a free real-time task manager built with Next.js and related workspace packages. They explain setup commands, runtime limits, coding rules, and checks that must pass.

Setting up Orbit, starting its database and development server, running verification, and following its Bun and Node.js compatibility rules.

They make the project's tooling and deployment constraints explicit, reducing failed builds and code that works locally but not in production.

orbit AGENTS.md — Instructions file by Noveum

Install

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.

agentmods

npx agentmods add instructions/noveum/orbit/agents-md

Clone the repo

git clone --depth 1 https://github.com/Noveum/orbit

Made for: Codex, OpenCode.

Per session 630 This file is loaded in full into every session.

When invoked 630 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00630	$0.00630
Opus 5	$0.00315	$0.00315
Sonnet 5	$0.00126	$0.00126
Haiku 4.5	$0.00063	$0.00063

Measured 3d ago against content hash 494c62b8596c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

AGENTS.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent instructions

Read CLAUDE.md first. It is the full context file for this repository and it is kept current: architecture, layout, the toolchain table, the conventions and the hard rules. This file exists so that assistants which look for AGENTS.md rather than CLAUDE.md find their way there.

CONTRIBUTING.md covers the human side: how to pick work, how to test, and how a pull request is reviewed.

The short version

Orbit is a free, realtime, keyboard-first task manager. One Next.js app on Vercel's node runtime, with the realtime hub and the MCP tools in workspace packages.

bun install
cp .env.example .env
bun run infra:up
bun run db:push && bun run db:test-setup && bun run db:seed
bun run dev
bun run verify     # lint, comment policy, types, tests

Rules that will fail the build

Bun only. No npm, pnpm, yarn or turbo. Every command starts with bun.
Shipped server code must not import a Bun built-in. The deployed runtime is node. Use postgres.js, ioredis, @aws-sdk/client-s3, node:fs/promises, @node-rs/argon2 and randomUUIDv7() from @orbit/shared/utils. Test files and apps/realtime are exempt.
No comments in code. bun run check-comments fails on anything that is not a functional directive such as @ts-expect-error or biome-ignore. Put the meaning in names and structure. Explanations go in the pull request or in docs/.
No em-dash characters anywhere, including commit messages.
No AI attribution in commits, branches, pull requests, code or docs.
Strict types. any and non-null assertions are lint errors. noUncheckedIndexedAccess and exactOptionalPropertyTypes are on. Parse external input with a Zod schema from @orbit/shared.
Tests live in each package's tests/ tree, mirroring src/, never beside the code. Import from bun:test.
Authorization goes through packages/shared/src/policy and is enforced on the server. A check that exists only in a component is not a check.

Read the full file on GitHub · 54 lines

Changes

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.

3d ago First seen · 54 lines · 630 tokens per session scan A 494c62b8596c

Subscribe to this mod's changes

orbit AGENTS.md is an instructions file published in the GitHub repository Noveum/orbit (29 stars, last pushed 3d ago), licensed Apache-2.0. It adds 630 tokens to every session, about $0.0032 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.

agile bun issue-tracker jira-alternative kanban linear-alternative

orbit AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Agent instructions

The short version

Rules that will fail the build

What this file has done since we first saw it

Other instructions, from other repositories

itsaplan AGENTS.md

itsaplan CLAUDE.md

bdui CLAUDE.md

bdui AGENTS.md

kanban CLAUDE.md

fff AGENTS.md