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/theeaglebyte/skylight-mcp/claude-mdgit clone --depth 1 https://github.com/TheEagleByte/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/theeaglebyte/skylight-mcp/claude-md)<a href="https://agentmods.dev/instructions/theeaglebyte/skylight-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/theeaglebyte/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 | $0.01203 | $0.01203 |
| Opus 5 | $0.00602 | $0.00602 |
| Sonnet 5 | $0.00241 | $0.00241 |
| Haiku 4.5 | $0.00120 | $0.00120 |
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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- skylight-mcp-fork CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 107 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.
Overview
MCP server enabling AI assistants to interact with the Skylight family calendar API (calendar, chores, lists, tasks, rewards, meals, photos).
Base API URL: https://app.ourskylight.com
Commands
npm install
npm run build # Compile TypeScript
npm run dev # Development with hot reload (tsx watch)
npm test # Run vitest tests
npm test -- dates # Run single test file (matches filename)
npm run test:coverage # Tests with coverage
npm run lint # ESLint
npm run typecheck # tsc --noEmit
npm run generate:types # Generate TypeScript types from OpenAPI spec
Architecture
Two-tier tool system:
api/endpoints/*.ts(11 modules) - Low-level HTTP wrappers for each API resourcetools/*.ts(9 modules) - MCP tool definitions with Zod parameter validation
Tool Registration: Each domain exports registerXxxTools(server) called from server.ts. Plus-only tools are conditionally registered based on subscription status.
Key files:
config.ts- Zod-validated env config supporting two auth methodsapi/client.ts- HTTP client with Bearer/Basic auth, auto-login, subscription status trackingapi/auth.ts- Login endpoint for email/password authenticationapi/generated-types.ts- Auto-generated types from OpenAPI specutils/dates.ts- Parses "today", "tomorrow", day names, YYYY-MM-DD
Authentication
Two methods supported (validated via Zod refinement in config.ts):
- Email/Password (recommended): Set
SKYLIGHT_EMAILandSKYLIGHT_PASSWORD. Server auto-logs in via POST /api/sessions and usesBasic base64(userId:token)format for subsequent requests. - Manual Token: Set
SKYLIGHT_TOKENand optionallySKYLIGHT_AUTH_TYPE(bearer/basic).
Both require SKYLIGHT_FRAME_ID (household identifier from API URLs like /api/frames/{frameId}/chores).
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.
- 6d ago First seen · 107 lines · 1,203 tokens per session scan A 2a5043e0c643
skylight-mcp CLAUDE.md is an instructions file published in the GitHub repository TheEagleByte/skylight-mcp (36 stars, last pushed 8mo ago), licensed MIT. It adds 1,203 tokens to every session, about $0.0060 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.
Other instructions, from other repositories
atom AGENTS.md
AGENTS.md instructions for rush86999/atom, covering agents.md — working standards for ai agents in this repo, 1. decide with the whole repo in context — no narrow fixes, 2. evidence over plausibility and 4. leave the trail navigable.
TimeTree-MCP CLAUDE.md
Claude Code instructions for ehs208/TimeTree-MCP, covering timetree mcp project guide, project purpose, current capabilities, architecture map and api behavior notes.
mcp-fantastical AGENTS.md
Instructions for aplaceforallmystuff/mcp-fantastical, covering agents.md - mcp-fantastical, tech stack, architecture, integration method and development.
cal-scheduler-mcp AGENTS.md
AGENTS.md instructions for limey/cal-scheduler-mcp, covering agents.md, what it is, when it fits, when it doesn't and install.
outlook-graph-skill AGENTS.md
Instructions for dbhq-uk/outlook-graph-skill, covering agents.md, what this is, layout, conventions and validating a change.
gaia AGENTS.md
AGENTS.md instructions for theexperiencecompany/gaia, a project described as: Your proactive personal AI assistant & companion for daily productivity 🌎.