agentmods.dev

orbit CLAUDE.md

orbit CLAUDE.md is an instructions file for coding agents from Noveum/orbit. It costs 3,943 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Orbit, a real-time task manager with features such as documents, files, notifications, GitHub integration, and an MCP server. They define the project’s tooling, code rules, validation requirements, and writing constraints.

In plain words
What is it for?
Use them when developing or reviewing Orbit code, running its checks, handling external input, or preparing project documentation and commits.
Why use it?
They keep contributions consistent with the project’s required runtime, strict typing, input validation, and style rules. They also prevent prohibited references and unsupported implementation choices.

Instructions file

not rated 29 5d ago A scan 3,943 tokens original Apache-2.0
View the source file Noveum/orbit
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/claude-md
Clone the repo
git clone --depth 1 https://github.com/Noveum/orbit

Wrote 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.

agentmods badge for orbit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/noveum/orbit/claude-md.svg)](https://agentmods.dev/instructions/noveum/orbit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/noveum/orbit/claude-md"><img src="https://agentmods.dev/badge/instructions/noveum/orbit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,943 This file is loaded in full into every session.
When invoked 3,943 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5 $0.03943 $0.03943
Opus 5 $0.01972 $0.01972
Sonnet 5 $0.00789 $0.00789
Haiku 4.5 $0.00394 $0.00394

Measured 5d ago against content hash ce4b10d59b19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orbit CLAUDE.md scanned grade A with 1 finding 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 5d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

| Subprocesses | `Bun.spawn`, `Bun.$` | `node:child_process` |
CLAUDE.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orbit

Free, realtime, keyboard-first task manager. The UX polish of the best paid task managers with the breadth of the open-source ones, plus docs, files, notifications, GitHub, and an MCP server. No pricing, no billing, no paid tiers anywhere.

Hard rules

  1. Bun is the package manager and the script runner. There is no pnpm, no npm, no yarn, no Turbo, and no node_modules produced by anything but bun install. Every command in this file starts with bun. The deployed runtime is node, so shipped code must not import a Bun built-in.
  2. No comments in code. Ever. bun run check-comments fails the build on any comment that is not a functional directive (@ts-*, biome-ignore, eslint-*, /*! license */). Make names and structure carry meaning.
  3. No AI attribution. Never mention Claude, Anthropic, Codex, or AI tooling in commits, branches, PRs, code, or docs.
  4. No em-dash characters in code, copy, docs, or commit messages. Use commas, colons, or separate sentences.
  5. Strict types only. any is a lint error. Non-null assertions are a lint error. noUncheckedIndexedAccess and exactOptionalPropertyTypes are on. Validate every external input with Zod.
  6. Every check green before you finish. bun run verify runs lint, comment policy, typecheck, and tests.

Bun is the toolchain, not the runtime

Bun installs, runs scripts, and runs tests. Shipped server code must not call a Bun built-in, because the web app runs on Vercel's node runtime: that is the only runtime where a Vercel function can upgrade a websocket, and /api/ws needs it. Anything imported from bun fails there with Cannot find module 'bun'.

Need Use Never use
Postgres postgres.js through drizzle-orm/postgres-js Bun.SQL, drizzle-orm/bun-sql, pg
Redis and pub/sub ioredis Bun.RedisClient, node-redis
Object storage @aws-sdk/client-s3 and @aws-sdk/s3-request-presigner Bun.S3Client
Reading and writing files node:fs/promises Bun.file(), Bun.write()
Hashing passwords @node-rs/argon2 (argon2id) Bun.password, bcrypt
Sortable ids randomUUIDv7() from @orbit/shared/utils Bun.randomUUIDv7(), ulid, nanoid
WebSocket server ws, upgraded by @vercel/functions Bun.serve({ websocket }) in shipped code
Running TypeScript bun file.ts tsx, ts-node
Tests bun test vitest, jest
Subprocesses Bun.spawn, Bun.$ node:child_process
Workspace script running bun run --filter '<pattern>' <script> turbo, nx, lerna
Env files bun --env-file=... dotenv

Read the full file on GitHub · 217 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.

  1. 5d ago First seen · 217 lines · 3,943 tokens per session scan A ce4b10d59b19

Subscribe to this mod's changes

orbit CLAUDE.md is an instructions file published in the GitHub repository Noveum/orbit (29 stars, last pushed 5d ago), licensed Apache-2.0. It adds 3,943 tokens to every session, about $0.0197 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agentsProject managementagilebunissue-trackerjira-alternativekanbanlinear-alternative
Related

Other instructions, from other repositories

itsaplan CLAUDE.md

Claude Code instructions for croffasia/itsaplan, a project described as: Open-source, self-hosted alternative to Linear and Plane. Project management and issue tracking where teams and AI agents work side by side to plan and ship products.

croffasia/itsaplan · 5 tokens

itsaplan AGENTS.md

AGENTS.md instructions for croffasia/itsaplan, covering agents.md, core coding principles, writing style (docs, comments, chat), golden rules and layout.

croffasia/itsaplan · 3,767 tokens

bdui CLAUDE.md

Claude Code instructions for assimelha/bdui, covering claude.md, project overview, development commands, run in development mode and build single binary for current platform.

assimelha/bdui · 3,316 tokens

bdui AGENTS.md

AGENTS.md instructions for assimelha/bdui, covering issue tracking with bd (beads), why bd?, quick start, issue types and priorities.

assimelha/bdui · 982 tokens

kanban CLAUDE.md

Claude Code instructions for kanban-rs/kanban, covering claude.md, project overview, architecture philosophy, solid principles applied and workspace structure.

kanban-rs/kanban · 4,406 tokens

flux AGENTS.md

Instructions for sirsjg/flux, covering agents.md, project overview, dogfooding, common commands and development.

sirsjg/flux · 1,140 tokens