mcp-nightscout: Instructions file for Claude Code

CLAUDE.md

mcp-nightscout CLAUDE.md is an instructions file for Claude Code from lozit/mcp-nightscout. It costs 3,770 tokens per session, scanned A, original, MIT.

Coding instructions for the mcp-nightscout project, including which planning, learning, vision, and decision files to read at the start of a session.

In plain words
What is it for?
Use them when working on mcp-nightscout, especially at the start of a session, after a substantial milestone, or before pushing code, creating a tag, or releasing.
Why use it?
They help an agent follow the project’s current direction and previously recorded lessons before changing code. They also require capturing important project updates at development checkpoints.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is lozit/mcp-nightscout's own configuration. It tells Claude Code how to work on mcp-nightscout itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-nightscout configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lozit/mcp-nightscout. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lozit/mcp-nightscout/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/lozit/mcp-nightscout

Made for: Claude Code.

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 mcp-nightscout CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lozit/mcp-nightscout/claude-md/github.svg)](https://agentmods.dev/instructions/lozit/mcp-nightscout/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lozit/mcp-nightscout/claude-md"><img src="https://agentmods.dev/badge/instructions/lozit/mcp-nightscout/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.

agentmods 80×15 button for mcp-nightscout CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lozit/mcp-nightscout/claude-md"><img src="https://agentmods.dev/badge/instructions/lozit/mcp-nightscout/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,770 This file is loaded in full into every session.
When invoked 3,770 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.03770 $0.03770
Opus 5 $0.01885 $0.01885
Sonnet 5 $0.00754 $0.00754
Haiku 4.5 $0.00377 $0.00377

Measured 8d ago against content hash f546e96c21a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-nightscout 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 8d 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.

CLAUDE.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — mcp-nightscout

This file is mutable and iterative. Update it after every Claude mistake or newly discovered convention. Target: < 200 lines.

Relationship with the global CLAUDE.md: this file is loaded in addition to the global (~/.claude/CLAUDE.md) — on conflict the global rule wins. Omitted here (your global already covers them): none.

Session start — read first, in order

  1. PLAN.md — where the project stands now
  2. docs/LEARNINGS.md — rules learned from past corrections (apply them!)
  3. docs/VISION.md — goal, scope, non-goals
  4. docs/decisions/0001-language-and-stack.md — the closed decisions and the seven binding constraints
  5. The artifacts of whatever is in progress per PLAN.md

Capture at checkpoints (don't wait to be asked)

The agent can't perceive "end of session" — so capture at the work boundaries it can see, and propose it proactively there without waiting for the user:

  • Before a git push, a tag, or a release — the highest-value, most reliable moment: pause and capture before shipping.
  • When a PLAN.md milestone is completed, or after a substantial chunk of work.

You can also trigger it yourself any time with /groundrules:checkpoint.

At that moment, three questions, each routed to where it belongs:

  1. Decided anything structural? → /groundrules:add-adr (docs/decisions/)
  2. Learned something that changes how to work here (incl. a blocker that cost 30+ min, with its fix)? → /groundrules:learn (docs/LEARNINGS.md)
  3. Caught the agent repeating a mistake, hallucinating, or drifting? → note it in docs/AGENT-EVALS.md and add the guard here or in .claude/rules/

Capture beats memory: if it's not written to the repo, it's gone next session.

Description

An MCP server giving Claude read-only access to a Nightscout instance: glucose readings, treatments, and deterministic server-side aggregates (mean, TIR, CV, GMI).

Read the full file on GitHub · 240 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. 8d ago First seen · 240 lines · 3,770 tokens per session scan A f546e96c21a2

Subscribe to this mod's changes

mcp-nightscout CLAUDE.md is an instructions file published in the GitHub repository lozit/mcp-nightscout (0 stars, last pushed 20d ago), licensed MIT. It adds 3,770 tokens to every session, about $0.0188 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens