What is standards CLAUDE.md?

A set of Claude Code instructions that routes project requests to relevant software standards. It supports product types such as APIs, web apps, mobile apps, data pipelines, and machine-learning services, along with language and security choices.

Use it to load standards for a project, combine choices such as Python and testing tools, and include security or compliance guidance.

It reduces the need to find and load every relevant standard by hand. The routing rules select documentation based on the product and technical options provided.

How williamzujkowski/standards configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to williamzujkowski/standards. 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/williamzujkowski/standards/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/williamzujkowski/standards

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/williamzujkowski/standards/claude-md/github.svg)](https://agentmods.dev/instructions/williamzujkowski/standards/claude-md)

Your own site

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

Per session 6,630 This file is loaded in full into every session.

When invoked 6,630 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	$0.06630	$0.06630
Opus 5.5	$0.02652	$0.02652
Sonnet 5.5	$0.01326	$0.01326
Haiku 4.5	$0.00663	$0.00663

Measured yesterday against content hash 411f8db27bb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-30, from the pricing page.

Security

Grade A, and why

standards 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 yesterday.

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 · 829 lines

How it starts

The opening of the file, as written. The whole thing — 829 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Configuration - Standards Router & SPARC Environment

🚀 Fast Path: Standards Auto-Loading

Quick Load by Product Type

@load product:api              # REST/GraphQL API service
@load product:web-service       # Full-stack web application
@load product:frontend-web      # React/Vue/Angular SPA
@load product:mobile           # iOS/Android application
@load product:data-pipeline    # ETL/ELT data workflow
@load product:ml-service       # ML training/inference service

Custom Combinations

@load [product:api + CS:python + TS:pytest]       # Python API
@load [product:frontend-web + FE:react + SEC:*]   # React with all security
@load [CS:python + TS:* + SEC:* + NIST-IG:full]  # Full compliance stack

How It Works

Reads config/product-matrix.yaml for product mappings
Resolves standard codes (CS, TS, SEC, etc.) to specific docs
Expands wildcards (SEC:* → all security standards)
Auto-includes NIST-IG:base when SEC is present
Loads relevant standards from docs/standards/ and related paths

Routing Contracts

Input: @load directive with product type and/or standard codes
Processing: Matrix resolution → wildcard expansion → NIST inclusion
Output: Loaded standards with implementation guidance

Implementation Note: The @load directive syntax shown above represents the planned interface. Current implementation requires using the skill-loader script:

python3 scripts/skill-loader.py load product:api
python3 scripts/skill-loader.py load skill:coding-standards/python

📘 Anthropic Skills.md Alignment

Compliance Status: 61/61 skills fully compliant (100%) ✅

Last Optimized: 2025-10-24 23:30:00 EDT (Phase 2 complete)

This repository implements Anthropic's canonical skills.md format with value-add extensions:

✅ Required Compliance (Anthropic Spec)

YAML Frontmatter with required fields:
- name: Skill identifier (<64 chars, lowercase/hyphens only)
- description: What the skill does and when to use it (<1024 chars)

Read the full file on GitHub · 829 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.

yesterday First seen · 829 lines · 6,630 tokens per session scan A 411f8db27bb4

Subscribe to this mod's changes

standards CLAUDE.md is an instructions file published in the GitHub repository williamzujkowski/standards (18 stars, last pushed 1mo ago), licensed MIT. It adds 6,630 tokens to every session, about $0.0265 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 2026-09-29.

Learning and teaching

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,406 tokens

standards: Instructions file for Claude Code