Borrowing it
Nothing to install: this file belongs to chrischall/skylight-mcp. 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/chrischall/skylight-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/chrischall/skylight-mcpWrote 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/chrischall/skylight-mcp/claude-md)<a href="https://agentmods.dev/instructions/chrischall/skylight-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/skylight-mcp/claude-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 5.1 | $0.07913 | $0.07913 |
| Opus 5 | $0.03957 | $0.03957 |
| Sonnet 5 | $0.01583 | $0.01583 |
| Haiku 4.5 | $0.00791 | $0.00791 |
Grade A, and why
skylight-mcp 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 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
TL;DR
MCP server for Skylight Calendar — 114 tools across calendar events (read+write), shared lists (read+write), chores and rewards (read+write), task-box items (read+write), meals (read+write), AI auto-creation (meal-plan + activity-idea generators with draft review/approve), messages and albums (read+write), photo/video upload, and frame/device/account settings + calendar + member/category management (read+write, incl. preset and custom-photo avatars).
Every request carries the skylight-api-version: 2026-05-01 header (src/client.ts), matching the official mobile app — without it some features 422 with "API version does not support …".
Auth resolution lives in src/auth.ts. Two credentials are accepted: a SKYLIGHT_REFRESH_TOKEN you already hold (skips the login endpoint entirely), or SKYLIGHT_EMAIL + SKYLIGHT_PASSWORD, which mint one via a headless OAuth2 authorization-code flow (Node-direct). See "Auth resolution" below.
The login is lazy and cached: resolveAuth() hands SkylightClient a bootstrap function rather than tokens, and TokenManager runs it only when the on-disk cache (src/token-store.ts) has nothing usable. A cached live token costs nothing; a cached expired one costs a refresh; only an empty or unusable cache spends a login. This matters because the login endpoint rate-limits (see the refreshFn note below) and a scale-to-zero host makes every start a cold one.
Auth resolution
src/auth.ts prefers a supplied SKYLIGHT_REFRESH_TOKEN and otherwise runs the headless email+password OAuth2 authorization-code flow below; with both set, a stale token falls back to logging in again. (Skylight rejects grant_type=password with unsupported_grant_type; no browser-bridge proxy is needed — no observed bot wall.)
The flow resolveAuth() → login() performs all steps against https://app.ourskylight.com:
GET /auth/session/new— scrape the Railsauthenticity_token, hold the_skylight_cloud_sessioncookie.POST /auth/session(form: authenticity_token, email, password;Origin/Referer= app.ourskylight.com) — 302 to/auth/session/successon success. Login must happen before the OAuth authorize step — hitting authorize first poisons the CSRF/session state.GET /oauth/authorize?client_id=skylight-mobile&response_type=code&scope=everything&redirect_uri=https://ourskylight.com/welcome&code_challenge=…&code_challenge_method=S256— 302 tohttps://ourskylight.com/welcome?code=…. PKCE is mandatory: withoutcode_challengethe server answers HTTP 400 "Code challenge is required." and issues no code (verified live 2026-08-31).POST /oauth/token(grant_type=authorization_code, client_id=skylight-mobile, scope=everything, code,code_verifiermatching step 3's challenge, redirect_uri,skylight_api_client_device_*device params, source=js-mobile) — returns{ access_token, refresh_token, expires_in: 86400 (24h, observed 2026-08-31 — it was 604800 when this flow was first captured, so read it from the response, never assume), token_type: Bearer }.
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 Changed · +2 lines · +607 tokens per session d77ffe10954b
- 4d ago Changed · +1 lines · +377 tokens per session 5769fe0dcb21
- 8d ago First seen · 184 lines · 6,929 tokens per session scan A c53d6943046f
skylight-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/skylight-mcp (8 stars, last pushed 3d ago), licensed MIT. It adds 7,913 tokens to every session, about $0.0396 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
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).
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.
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).
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.