Borrowing it
Nothing to install: this file belongs to crclabs-hq/GateTest. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/crclabs-hq/GateTest/main/CLAUDE.mdgit clone --depth 1 https://github.com/crclabs-hq/GateTestWrote 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.
[](https://agentmods.dev/instructions/crclabs-hq/gatetest/claude-md)<a href="https://agentmods.dev/instructions/crclabs-hq/gatetest/claude-md"><img src="https://agentmods.dev/badge/instructions/crclabs-hq/gatetest/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.
<a href="https://agentmods.dev/instructions/crclabs-hq/gatetest/claude-md"><img src="https://agentmods.dev/badge/instructions/crclabs-hq/gatetest/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.16447 | $0.16447 |
| Opus 5.5 | $0.06579 | $0.06579 |
| Sonnet 5.5 | $0.03289 | $0.03289 |
| Haiku 4.5 | $0.01645 | $0.01645 |
Grade D, and why
GateTest CLAUDE.md scanned grade D with 3 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 26d 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.
- **Env:** `/opt/<service>/.env` on the box, chmod 600. Secrets flow keyboard → Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -sSL https://raw.githubusercontent.com/crclabs-hq/gatetest/main/integrations/scripts/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sSL https://raw.githubusercontent.com/crclabs-hq/gatetest/main/integrations/scripts/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 828 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GATETEST — THE BIBLE
This document is the single source of truth for GateTest. Read it FIRST. Reference it ALWAYS. Violate it NEVER.
THE PRIME DIRECTIVE
GateTest kills SonarQube. GateTest kills Snyk. GateTest kills every fragmented QA tool.
Code quality has never been unified. Teams duct-tape 10+ tools together — different configs, different dashboards, different billing. We are the unification. There is no second place. We dominate or we die. Every line of code, every component, every decision, every commit must serve this mission.
The standard: 80-90% ahead of every competitor at all times. Not 10%. Not 30%. Eighty to ninety percent.
If a competitor closes the gap, we accelerate. If new technology threatens our lead, we absorb it. We are not in a race — we are lapping the field.
THE BIBLE RULE
Before ANY new build, ANY refactor, ANY significant change — READ THIS FILE FIRST.
This file is read at the start of every session. It is referenced before every architectural decision. It is updated at the end of every session. No work happens outside the framework defined here.
No scatter-gun. No drift. No "just this once." No chicken scratchings. Every action ties back to this document.
The Bible's library — where the detail lives
The Bible holds rules + current truth only. Deep reference material lives in docs/ — read the one that matches your task BEFORE building:
| File | Read it when... |
|---|---|
docs/ARCHITECTURE.md |
Touching the stack, module system, serverless rules, key files, or env vars |
docs/MODULES.md |
Adding/changing a module, or writing competitive/marketing copy about module coverage |
docs/ROADMAP.md |
Picking up new work — evolution tiers, Inclusive Agentic QA spec, open Known Issues, remote-MCP distribution plan |
docs/HISTORY.md |
Wondering whether something was already built/decided — completed build plans, all version changelogs, resolved Known Issues |
docs/DOCTRINE.md |
Before touching the engine or a rule — the fourteen working principles, each with the defect that proved it and the method that prevents it |
docs/THE-FIFTY.md |
Picking up new work — the current fifty-move plan with status and evidence per move; the work queue |
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.
- 26d ago Changed · +21 lines · +262 tokens per session a67539ac4824
- 28d ago Changed · +1 lines · +164 tokens per session 44c5623f07ef
- 29d ago Changed · +157 tokens per session f6642edb12ae
- 1mo ago Changed · +2 lines · +79 tokens per session c8cf17fd26ca
- 1mo ago Changed · -1 lines · +85 tokens per session a67fc15fe2b3
- 1mo ago Changed · +24 lines · +938 tokens per session 5e0e62cb3da9
- 1mo ago Changed · +29 lines · +1,176 tokens per session 4394b947e04f
- 1mo ago Changed · +52 lines · +812 tokens per session scan C → D 2e72c1eb14f4
- 1mo ago Changed · +1 lines · +283 tokens per session 1907a57f72c8
- 1mo ago First seen · 699 lines · 12,491 tokens per session scan C 6d4436ec96dc
GateTest CLAUDE.md is an instructions file published in the GitHub repository crclabs-hq/GateTest (0 stars, last pushed 26d ago), licensed MIT. It adds 16,447 tokens to every session, about $0.0658 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.