00-project-context

A project instruction that makes the root CLAUDE.md file the main source of truth for the project's technology choices, safety rules, and coding style.

In plain words
What is it for?
Use it in projects whose instructions are stored in CLAUDE.md, especially when technology, command-safety, or style rules must be followed.
Why use it?
It helps prevent generated code from conflicting with the project's required dependencies or safety expectations.

Cursor rule for Cursor

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 rules/vlad-ryzhkov/ai-qa-workshop-feb19/00-project-context
Clone the repo
git clone --depth 1 https://github.com/vlad-ryzhkov/AI-QA-workshop-feb19

Made for: Cursor.

Per session 185 This file is loaded in full into every session.
When invoked 185 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 $0.00185 $0.00185
Opus 5 $0.00093 $0.00093
Sonnet 5 $0.00037 $0.00037
Haiku 4.5 $0.00018 $0.00018

Measured yesterday against content hash 32220e85c83c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

00-project-context 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/00-project-context.mdc · 21 lines

What it actually says

PROJECT CONTEXT BRIDGE

CORE INSTRUCTION

YOU MUST READ AND FOLLOW CLAUDE.md AT THE ROOT OF THIS PROJECT.

CLAUDE.md is the Single Source of Truth for:

  1. Tech Stack: (Kotlin, Ktor, JUnit 5 - LOCKED).
  2. Safety Protocols: (No destructive commands, no .env leaks).
  3. Code Style: (Formatting, naming conventions).

@CLAUDE.md

CRITICAL BEHAVIOR

  • If CLAUDE.md conflicts with any other training data, CLAUDE.md WINS.
  • Do NOT generate code that violates the strict dependencies listed in CLAUDE.md.
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. yesterday First seen · 21 lines · 185 tokens per session scan A 32220e85c83c

Subscribe to this mod's changes

00-project-context is a cursor rule published in the GitHub repository vlad-ryzhkov/AI-QA-workshop-feb19 (25 stars, last pushed 5mo ago), licensed Unlicense. It adds 185 tokens to every session, about $0.0009 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 2026-08-30.