nightscout: Instructions file for Claude Code

CLAUDE.md

nightscout CLAUDE.md is an instructions file for Claude Code from b77ai/nightscout. It costs 1,504 tokens per session, scanned A, original, MIT.

Project instructions for an MCP server that connects diabetes-management data from Nightscout, a service for sharing glucose and treatment information. They describe the server's files, technology stack, settings, and process for adding tools.

In plain words
What is it for?
Use them when working on Nightscout API integration, authentication, logging, tests, deployment, or new MCP tools.
Why use it?
They give an agent the project context needed to change the server safely, including where API calls belong and how authentication is configured.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is b77ai/nightscout's own configuration. It tells Claude Code how to work on 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 nightscout configures →

Reuse

Borrowing it

Nothing to install: this file belongs to b77ai/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/b77ai/nightscout/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/b77ai/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 nightscout CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/b77ai/nightscout/claude-md/github.svg)](https://agentmods.dev/instructions/b77ai/nightscout/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/b77ai/nightscout/claude-md"><img src="https://agentmods.dev/badge/instructions/b77ai/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 nightscout CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/b77ai/nightscout/claude-md"><img src="https://agentmods.dev/badge/instructions/b77ai/nightscout/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,504 This file is loaded in full into every session.
When invoked 1,504 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 $0.01504 $0.01504
Opus 5.5 $0.00602 $0.00602
Sonnet 5.5 $0.00301 $0.00301
Haiku 4.5 $0.00150 $0.00150

Measured 2mo ago against content hash 25396c28b893, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 2mo 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 · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Nightscout

FastMCP server providing tools for diabetes type 1 management via Nightscout API.

Key files

  • src/server.py — MCP tools + auth middleware + health endpoint
  • src/nightscout_client.py — HTTP client for Nightscout REST API v1
  • src/log_filter.py + src/log_config.yaml — JSON logging, filters /health
  • tests/test_auth.py — auth middleware tests (pytest-asyncio)

Stack

  • Python 3.12, FastMCP, httpx, uvicorn
  • Docker → GitLab CI → Kubernetes (deploy/ templates)

Environment variables

  • NIGHTSCOUT_URL — Nightscout instance base URL
  • NIGHTSCOUT_API_SECRET — API secret (hashed SHA1)
  • NIGHTSCOUT_TOKEN — readable token (alternative to api-secret)
  • NIGHTSCOUT_TIMEOUT — request timeout (default 30s)
  • MCP_AUTH_TOKEN — MCP server auth token (optional for local dev)

Adding a new tool

  1. If it needs a new API call, add it to nightscout_client.py
  2. Add @mcp.tool() function in server.py with clear docstring
  3. Run docker compose up --build to test locally

2. Coding Practices (Clean Code)

  • SOLID & Modular: Use Clean Code principles. E.g. keep functions small and focused on one task.
  • No Redundancy: Avoid "huge texts" for small clarifications. Keep code self-documenting.
  • Formatting:
    • Black for Python (max line length 79).

3. Testing

Unit Test Writing Guidelines

1. Structure Every Test with Given-When-Then comments
  • Given: set up preconditions and test data.
  • When: execute one behavior/action under test.
  • Then: assert the observable outcome.
  • If action and expectation are tightly coupled (for example exception checks), a combined When/Then block is acceptable.
2. Name Tests as Readable Behavior Statements
  • Use names that describe scenario plus expected outcome.
  • Recommended pattern: scenario_expected_result.
  • Prefer descriptive names over generic names like test1 or shouldWork.
  • A reader should understand what the test proves without reading the full body.
3. Keep One Behavior per Test
  • Each test should validate one rule or behavior.
  • Avoid mixing unrelated assertions in one test.
  • Split into multiple tests if multiple behaviors need verification.

Read the full file on GitHub · 138 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. 2mo ago First seen · 138 lines · 1,504 tokens per session scan A 25396c28b893

Subscribe to this mod's changes

nightscout CLAUDE.md is an instructions file published in the GitHub repository b77ai/nightscout (7 stars, last pushed 3mo ago), licensed MIT. It adds 1,504 tokens to every session, about $0.0060 per session on Opus 5.5. 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

nightscout CLAUDE.md compared with instructions from other repositories

nightscout CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
nightscout CLAUDE.mdb77ai/nightscoutInstructions file73mo agoMITA1,504Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode