What is personal-health-graph CLAUDE.md?

Repository instructions for a Personal Health Graph: a collection of structured Markdown files for organizing and analysing health data. It is not a conventional software project, so it has no build step, tests, or dependencies.

Use it to import health files, set up the graph, check stale links, and analyse supplements, symptoms, sleep, wearable data, and patterns.

It explains the repository’s working rules and available analyses before an agent changes files or processes health data.

How gtr36/personal-health-graph configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to gtr36/personal-health-graph. 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/gtr36/personal-health-graph/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/gtr36/personal-health-graph

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gtr36/personal-health-graph/claude-md/github.svg)](https://agentmods.dev/instructions/gtr36/personal-health-graph/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/gtr36/personal-health-graph/claude-md"><img src="https://agentmods.dev/badge/instructions/gtr36/personal-health-graph/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/gtr36/personal-health-graph/claude-md"><img src="https://agentmods.dev/badge/instructions/gtr36/personal-health-graph/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,753 This file is loaded in full into every session.

When invoked 1,753 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.

Model	Per session	Once invoked
Fable 5.1	$0.01753	$0.01753
Opus 5.5	$0.00701	$0.00701
Sonnet 5.5	$0.00351	$0.00351
Haiku 4.5	$0.00175	$0.00175

Measured 2mo ago against content hash 2eac8749c308, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

personal-health-graph 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 · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 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.

What this repo is

Personal Health Graph (PHG) is a structured markdown file system — not a software project. There is no build step, no test suite, no dependencies. The "code" is methodology: structured natural language skill files that instruct LLMs how to analyze health data.

How to work with this repo

Running skills

Skills are in skills/*.md and skills/workflows/*.md. To run a skill, read the skill file and follow its instructions against the relevant data files it specifies in its reads: frontmatter field.

Entry point skills:

skills/INTAKE.md — process files dropped in inbox/ into structured PHG files
skills/QUICKSTART.md — guided onboarding wizard; run if the graph is newly set up
skills/MAINTENANCE.md — scheduled audit of staleness and cross-reference validity

Analysis skills (require populated data first):

skills/SUPPLEMENT_REVIEW.md — evaluate supplement stack against labs and genetics
skills/SYMPTOM_ANALYSIS.md — correlate symptoms with sleep, wearables, supplements
skills/PATTERN_DETECTION.md — full-history scan for correlations and anomalies
skills/DOCTOR_PREP.md — compile structured visit summary for a provider
skills/MASTER_ANALYSIS.md — comprehensive 5-phase analysis
skills/HEALTH_MEMO.md — Amazon-style narrative health briefing
skills/BASELINE_REPORT.md — first-run assessment with gap analysis
skills/RISK_ASSESSMENT.md — cardiovascular and genetic risk review
skills/EXPERIMENT.md — design and evaluate N-of-1 self-experiments (writes EXPERIMENTS.md)
skills/FACT_AUDIT.md — re-verify a prior report's claims against primary sources
skills/SPECIALIST_TRANSLATOR.md — specialty-native handoff briefs
skills/TIMELINE.md — rebuild TIMELINE.md, the derived chronological event spine
skills/DASHBOARD.md — render the graph into a self-contained HTML dashboard (injects data into templates/dashboard_shell.html; never edit the shell's markup or add external resources)

Read the full file on GitHub · 110 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.

2mo ago First seen · 110 lines · 1,753 tokens per session scan A 2eac8749c308

Subscribe to this mod's changes

personal-health-graph CLAUDE.md is an instructions file published in the GitHub repository gtr36/personal-health-graph (20 stars, last pushed 2mo ago), licensed MIT. It adds 1,753 tokens to every session, about $0.0070 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.

Memory and context

personal-health-graph CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
personal-health-graph CLAUDE.mdgtr36/personal-health-graph	Instructions file	20	2mo ago	MIT	A	1,753	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

personal-health-graph: Instructions file for Claude Code