module-gates CLAUDE.md

Project instructions for module-gates, a code extension whose source is organized into modules, or directories. They define the project's file relationships, conventions, and communication style.

In plain words
What is it for?
They help distinguish files that are internal, external, sibling, or child files, locate source and test code, use the task-directory convention, and answer questions before making edits.
Why use it?
They give an agent a shared vocabulary for navigating folders and help it follow the project's concise writing and coding rules.

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/cuzfrog/module-gates/claude-md
Clone the repo
git clone --depth 1 https://github.com/cuzfrog/module-gates
Per session 1,276 This file is loaded in full into every session.
When invoked 1,276 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 $0.01276 $0.01276
Opus 5 $0.00638 $0.00638
Sonnet 5 $0.00255 $0.00255
Haiku 4.5 $0.00128 $0.00128

Measured 2d ago against content hash 275c8e3c6225, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

module-gates 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 2d 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 · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Rules

Code Structure

  • src/ - extention source
  • test/ - unit tests
  • .tasks/ - local development plan directory, e.g. .tasks/ISSUE-2/ for Github issue #2.

Glossary

Given the example code structure:

src/
   file1.ts
   file2.ts
   sub1/
      file3.ts
   sub2/
      file4.ts
  • Module: a directory. src/ is a module, src/sub1/ is a module.
  • Siblings: files in the same directory. src/file1.ts and src/file2.ts are siblings.
  • Children: files in a sub-directory. src/sub1/file3.ts and src/sub2/file4.ts are children of module src.
  • External: files in external modules. file1.ts is an external file from module sub1. file4.ts is an external file from module sub1.
  • Internal: files in the same module. file1.ts is an internal file of module src, file3.ts is an internal file of module sub1 and module src.

Also refer to @README.md

Conversational Style

  • Keep answers short and concise
  • No emojis in commits, issues, PR comments, or code
  • When the user asks a question, answer it first before making edits or running implementation commands.
  • When writing text, think from the reader's perspective, write only what they need to know.
  • When writing to README, be concise.
  • If you want to ask user, simply print the questions, there's no such a ask_user tool.

Code Conventions

  • No any types, No enums, No inline imports, No Classes
  • Use only erasable TypeScript syntax compatible with Node strip-only mode in TypeScript. Do not use constructor parameter properties, enum, namespace/module, import =, export =, or other TypeScript constructs that require JavaScript emit. Use explicit fields and constructor assignments instead of parameter properties.
  • Public types, contract, methods, higher-level abstractions should be at the top of the files, private implementation details should be at the bottom. If a private function only is used in the same file, it should be below its callers. See below section Single file layout.
  • Do not add comments except it's a consequential information and the code itself cannot tell.

Read the full file on GitHub · 88 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. 2d ago First seen · 88 lines · 1,276 tokens per session scan A 275c8e3c6225

Subscribe to this mod's changes

module-gates CLAUDE.md is an instructions file published in the GitHub repository cuzfrog/module-gates (13 stars, last pushed 10d ago), licensed MIT. It adds 1,276 tokens to every session, about $0.0064 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 2026-08-31.