What is standardgraph CLAUDE.md?

Project instructions for StandardGraph, a local tool that lets Claude search and compare more than 175,000 education standards from 310 curriculum systems. Education standards are the learning goals schools use for subjects and grade levels.

Use them when developing, testing, or maintaining the StandardGraph MCP server and its standards database and data-ingestion pipeline.

They give the coding agent the project’s structure, data locations, important facts, and test commands so it can work on the repository with the right context.

standardgraph CLAUDE.md — Instructions file for coding agents by swoopeagle: Project instructions for StandardGraph, a local tool that lets…

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.

agentmods

npx agentmods add instructions/swoopeagle/standardgraph/claude-md

Clone the repo

git clone --depth 1 https://github.com/swoopeagle/standardgraph

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/swoopeagle/standardgraph/claude-md.svg)](https://agentmods.dev/instructions/swoopeagle/standardgraph/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/swoopeagle/standardgraph/claude-md"><img src="https://agentmods.dev/badge/instructions/swoopeagle/standardgraph/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,930 This file is loaded in full into every session.

When invoked 2,930 The same file — it is already loaded in full.

Security scan B 1 finding. Scan, not verified.

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	$0.02930	$0.02930
Opus 5	$0.01465	$0.01465
Sonnet 5	$0.00586	$0.00586
Haiku 4.5	$0.00293	$0.00293

Measured 4d ago against content hash 2ea2f81b1899, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

standardgraph CLAUDE.md scanned grade B with 1 finding 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 4d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

`UserName: devos` set (without it they run as root and the venv/DB paths break).

CLAUDE.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

StandardGraph — Claude Code context

What this is

FastMCP server exposing 175,000+ education standards across 310 curriculum systems as six MCP tools for Claude Desktop. Standards cover Math, Science, ELA, Social Studies, CS, Arts, and World Languages.

Architecture

packages/
  common-core/       → PyPI package "standardgraph" — the MCP server
    src/common_core/
      server.py      → all six MCP tools (search, lookup, progression, learning_path, map, list)
      config.py      → DB_PATH resolution (~/.standardgraph/common_core.db)
  ingestion/         → pipeline: fetchers → embed → relate → crosswalk
  shared/            → shared DB helpers

data/common_core.db          → dev/pipeline DB (used by overnight_run.sh)
~/.standardgraph/common_core.db  → installed user DB (used by MCP server)

scripts/
  mcp_test.py        → 333-test suite (imports server directly, no MCP protocol)
  overnight_run.sh   → full ingestion pipeline (run on Mac Studio overnight)
  dashboard.sh       → hardware + pipeline progress dashboard
  progress.sh        → pipeline-only progress view

Key facts

DB size: ~1.9 GB
Standards: 175,738 across 310 systems (incl. CCSS sub-standard decomposition, source-side decomposition of 11 high-bundling systems, CCSS Mathematical Practice standards, the 2026-07 international expansion incl. 10 African systems, and the 2026-07-15 math grade-coverage fill-in for 11 countries)
Crosswalk rows: ~208,442 — hub-centric (CCSS for math, NGSS for science, etc.) PLUS ~88,944 direct within-family country-to-country math edges (see crosswalk_engine/direct_family.py; tagged direct_family in notes). map_standard serves direct edges automatically, two-hop-via-CCSS is the fallback.
Crosswalk quality scores: ALL 208,442 crosswalks now carry a 1–5 LLM quality score (100%) — completed 2026-07-18 via two overnight Ollama fleet runs (Studio + Mini 2 + IWPC GPU, qwen2.5:14b): the 88,944 direct-family math edges, then the 41,697 hub-centric edges (mostly ELA/Sci/SS). 37,335 edges carry flagged_for_review=1 and are suppressed from default map_standard results. Flagging policy differs by layer: direct-family flags score ≤2; hub-centric flags only score 1 (hub 2s are often valid-but-grade-shifted, and map_standard already ranks by score). Non-math hub rationales were re-scored with a subject-neutral prompt (the initial fleet prompt said "math", polluting ~2,520 non-math rationales — fixed). Note: scores span calibration regimes (earlier Sonnet mode=4; fleet 14b generous top-end) — directional weak/strong signal intact.
Relationships: ~3.79M rows (prerequisites/successors)
Ollama host: http://169.254.1.1:11434 (Mac Studio via Thunderbolt Bridge from Mini 2 — 0.4ms RTT)
HuggingFace dataset: swoopeagle/standardgraph (file: common_core.db)
PyPI package: standardgraph

Read the full file on GitHub · 199 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.

4d ago First seen · 199 lines · 2,930 tokens per session scan B 2ea2f81b1899

Subscribe to this mod's changes

standardgraph CLAUDE.md is an instructions file published in the GitHub repository swoopeagle/standardgraph (5 stars, last pushed 1mo ago), licensed MIT. It adds 2,930 tokens to every session, about $0.0146 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Learning and teaching advanced-placement ccss claude common-core curriculum curriculum-alignment

standardgraph CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade B, and why

Asks for rootmediumPrivilege escalation

How it starts

StandardGraph — Claude Code context

What this is

Architecture

Key facts

What this file has done since we first saw it

Other instructions, from other repositories

exam-revision-handbook AGENTS.md

AI-learning-by-claude-code CLAUDE.md

AI-learning-by-claude-code AGENTS.md

ab900 CLAUDE.md

obsidian-university-workflow CLAUDE.md

anki-mcp-server CLAUDE.md