strata CLAUDE.md

strata CLAUDE.md is an instructions file for coding agents from makedirectory/strata. It costs 1,291 tokens per session, scanned A, original, Apache-2.0.

A Claude Code instruction file for Strata, describing how its commands, architecture, data flow, and saved data fit together. It also lists commands for developing, testing, checking types, formatting, and building the project.

In plain words
What is it for?
Use it when working on the Strata codebase, including running its development server, tests, documentation build, MCP server, or pre-release checks.
Why use it?
It gives the coding agent the project rules and checks needed to make changes without breaking its structure.

Instructions file

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/makedirectory/strata/claude-md
Clone the repo
git clone --depth 1 https://github.com/makedirectory/strata

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 strata CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/makedirectory/strata/claude-md.svg)](https://agentmods.dev/instructions/makedirectory/strata/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/makedirectory/strata/claude-md"><img src="https://agentmods.dev/badge/instructions/makedirectory/strata/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,291 This file is loaded in full into every session.
When invoked 1,291 The same file — it is already loaded in full.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.01291 $0.01291
Opus 5 $0.00646 $0.00646
Sonnet 5 $0.00258 $0.00258
Haiku 4.5 $0.00129 $0.00129

Measured 3d ago against content hash edf20dabf25e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

strata 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 3d 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 · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 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.

Commands

npm run dev            # Next.js dev server — product at /, docs at /docs (localhost:3000)
npm run build          # production build + prerender docs
npm test               # vitest run (one-shot)
npm run test:watch     # vitest watch mode
npm run test:update    # re-record snapshots (*.snapshot.test.ts) — see caveat below
npm run test:coverage  # vitest with v8 coverage
npm run typecheck      # tsc --noEmit
npm run lint           # next lint
npm run format         # prettier --write .   (format:check for CI-style check)
npm run mcp            # run the MCP server over stdio (npx tsx, no build step)

Run a single test file or pattern (vitest passes args through):

npm test -- src/aws/registry.test.ts        # one file
npm test -- -t "validates relationships"    # by test-name substring

Pre-PR gate (CI runs all of these on Node 22 and 24; local Node is >=24):

npm run format && npm run lint && npm run typecheck && npm test && npm run build

The core architectural invariant

Everything visual and analytical is derived from the service registry — nothing about a cloud service is hardcoded in the UI. The palette, node colours/icons, the auto-generated inspector form, search, validation, IaC import/export, and cost all read from src/aws/registry.ts, which aggregates per-category catalogs.

Consequence: adding a service is a single ServiceDefinition entry in the matching catalog under src/aws/services/ (or src/gcp/services/, src/azure/services/). Use src/aws/services/networking.ts as the template. Do not add UI branches for specific services — if you find yourself special-casing a service in a component, the data probably belongs in its ServiceDefinition instead.

The cross-provider join key is nativeType (CloudFormation type for AWS, Cloud Asset Inventory type for GCP, ARM type for Azure). AWS entries fall back to cfnType, so existing AWS catalogs need no edit. This key is what ties a registry entry to IaC import/export and live-discovery mapping.

Read the full file on GitHub · 102 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. 3d ago First seen · 102 lines · 1,291 tokens per session scan A edf20dabf25e

Subscribe to this mod's changes

strata CLAUDE.md is an instructions file published in the GitHub repository makedirectory/strata (0 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,291 tokens to every session, about $0.0065 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 2026-09-01.