Borrowing it
Nothing to install: this file belongs to justinwilliames/orbit-for-claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/justinwilliames/orbit-for-claude/main/CLAUDE.mdgit clone --depth 1 https://github.com/justinwilliames/orbit-for-claudeWrote 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/justinwilliames/orbit-for-claude/claude-md)<a href="https://agentmods.dev/instructions/justinwilliames/orbit-for-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/justinwilliames/orbit-for-claude/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/justinwilliames/orbit-for-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/justinwilliames/orbit-for-claude/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01756 | $0.01756 |
| Opus 5 | $0.00878 | $0.00878 |
| Sonnet 5 | $0.00351 | $0.00351 |
| Haiku 4.5 | $0.00176 | $0.00176 |
Grade A, and why
orbit-for-claude CLAUDE.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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — orbit-for-claude
What this repo is
The Orbit MCP extension for Claude Desktop, packaged as a .mcpb bundle. Local-only stdio transport. Distributed from the private Tigris bucket fronted by get-orbit's /api/mcpb-download. Sibling repos: get-orbit (website + admin), orion-by-orbit (macOS dock companion), orbit-dictation (menu-bar dictation fork).
Two surfaces in one extension:
- Skill router (
orbit.md) — disambiguates the user's request and selects the right specialist protocol fromskills/. - Tool layer (
server/) — the tools backing the skills. ESM JS, no TypeScript, Zod for input validation.
(Exact skill/tool counts live in manifest.json and are kept in sync by
scripts/sync-counts.mjs — this file deliberately doesn't repeat them as a
number, since it drifted twice and nothing here needs the precise figure.)
Repo map
| Path | What's inside |
|---|---|
manifest.json |
MCPB manifest. Version is the source of truth; package.json.version must match (CI check script enforces). |
orbit.md |
Master skill router — what Claude reads first to decide which protocol to apply. |
skills/*.md |
One specialist protocol per lifecycle/CRM concern. YAML frontmatter (name, description) drives Claude's trigger logic. |
server/index.js |
Monolithic entry point: tool registration + dispatch + telemetry. ~4,800 LoC. Known target for splitting — see Deferred refactors below. |
server/catalog.js |
Skill registry + manifest builder. Loaded at startup. |
server/braze-*.js |
Braze API client surface, fragmented across 4 files. Known target for consolidation. |
server/lifecycle-diagrams.js |
SVG → PNG diagram rendering (~2,500 LoC). |
server/input-limits.js |
Central per-field caps used by every Zod schema. Never bypass. |
scripts/build-extension.js |
esbuild bundle into .mcpb-build/, ready for mcpb pack. |
scripts/fetch-guides.mjs / fetch-courses.mjs |
Sync practitioner guide and course content from get-orbit. |
tests/ |
Integration tests + fixtures. No unit coverage on calculators/validators yet. |
evals/ |
Skill-router evaluation harness. |
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 Changed · +4 lines · +42 tokens per session 51482933e764
- 8d ago First seen · 89 lines · 1,714 tokens per session scan A 627dd858d468
orbit-for-claude CLAUDE.md is an instructions file published in the GitHub repository justinwilliames/orbit-for-claude (0 stars, last pushed today), licensed MIT. It adds 1,756 tokens to every session, about $0.0088 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.