What is nightscout-cgm?

A workflow for analyzing continuous glucose monitor data from Nightscout, a system that stores and displays blood-glucose readings.

It helps retrieve current readings, analyze trends, estimate A1C, calculate time in range and variability, compare periods, find recurring alerts, and create reports.

It turns glucose readings into trends and summaries that are easier to review than raw measurements alone.

nightscout-cgm — Skill for Claude Code and Codex by shanselman

Install

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.

Any agent

npx skills add shanselman/nightscout-cgm-skill --skill nightscout-cgm-skill

Clone the repo

git clone --depth 1 https://github.com/shanselman/nightscout-cgm-skill

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/shanselman/nightscout-cgm-skill/nightscout-cgm-skill/github.svg)](https://agentmods.dev/skills/shanselman/nightscout-cgm-skill/nightscout-cgm-skill)

Your own site

<a href="https://agentmods.dev/skills/shanselman/nightscout-cgm-skill/nightscout-cgm-skill"><img src="https://agentmods.dev/badge/skills/shanselman/nightscout-cgm-skill/nightscout-cgm-skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/shanselman/nightscout-cgm-skill/nightscout-cgm-skill"><img src="https://agentmods.dev/badge/skills/shanselman/nightscout-cgm-skill/nightscout-cgm-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,242 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.03242
Opus 5.5	$0.00020	$0.01297
Sonnet 5.5	$0.00010	$0.00648
Haiku 4.5	$0.00005	$0.00324

Measured 2mo ago against content hash 5b8dd92f3406, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nightscout-cgm 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/cgm.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

SKILL.md · 306 lines

How it starts

The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nightscout CGM Analysis Skill

This skill provides tools for fetching and analyzing Continuous Glucose Monitor (CGM) data from Nightscout.

⚠️ Before Making Changes

Always run tests before and after modifying cgm.py:

cd <skill-path>
python -m pytest tests/ -q           # Quick check (281+ tests)
python -m pytest tests/ --cov=scripts  # With coverage

Available Commands

Run the cgm.py script from this skill's scripts/ directory:

python <skill-path>/scripts/cgm.py <command> [options]

Where <skill-path> is the location where this skill is installed (e.g., ~/.copilot/skills/nightscout-cgm, .github/skills/nightscout-cgm, or .claude/skills/nightscout-cgm).

Commands

Command	Description
`current`	Get the latest glucose reading
`analyze [--days N]`	Analyze CGM data (default: 90 days)
`report [--days N] [--output PATH] [--open]`	Generate interactive, PDF-printable HTML report with charts
`goals [view	set
`compare --period1 P1 --period2 P2`	Compare two time periods side-by-side
`alerts [--days N]`	Get trend alerts for recurring patterns
`refresh [--days N]`	Fetch latest data from Nightscout
`auto-refresh [view	set
`patterns [--days N]`	Find interesting patterns (best/worst times, problem areas)
`query [options]`	Query with filters (day of week, time range)
`day <date> [options]`	View all readings for a specific date
`worst [options]`	Find your worst days for glucose control
`chart [options]`	Terminal visualizations (heatmap, sparkline, day chart)
`pump`	Get current pump status (IOB, COB, predicted glucose) *
`treatments [--hours N]`	Get recent treatments (boluses, temp basals, carbs) *
`events [--tag TEXT] [--days N]`	Correlate glucose response around existing Nightscout treatments/events *
`ages [--count N]`	Get CAGE/SAGE/IAGE from Site/Sensor/Insulin Change events *
`profile`	Get pump profile settings (basal rates, ISF, carb ratios) *

Read the full file on GitHub · 306 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/cgm.py 261 KB runs code

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.

2mo ago First seen · 306 lines · 49 tokens per session scan A 5b8dd92f3406

Subscribe to this mod's changes

nightscout-cgm is a skill published in the GitHub repository shanselman/nightscout-cgm-skill (59 stars, last pushed 5mo ago), licensed MIT. It adds 49 tokens to every session and 3,242 once invoked, about $0.0002 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 2026-08-30.

Analytics and metrics Scientific

nightscout-cgm next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
nightscout-cgmshanselman/nightscout-cgm-skill	Skill	59	5mo ago	MIT	A	49	Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-plugins	Skill	35k	2d ago	Apache-2.0	A	123	Claude Code
exploratory-data-analysisK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	83	Claude Code
matlabK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	44	Claude Code
phylogeneticsK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	71	Claude Code, Codex
research-engineerdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	43	Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmed	Skill	5.8k	yesterday	Apache-2.0	A	205	Claude Code