Borrowing it
Nothing to install: this file belongs to vanssata/jetbrains-claude-subscription. 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/vanssata/jetbrains-claude-subscription/master/CLAUDE.mdgit clone --depth 1 https://github.com/vanssata/jetbrains-claude-subscriptionWrote 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/vanssata/jetbrains-claude-subscription/claude-md)<a href="https://agentmods.dev/instructions/vanssata/jetbrains-claude-subscription/claude-md"><img src="https://agentmods.dev/badge/instructions/vanssata/jetbrains-claude-subscription/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/vanssata/jetbrains-claude-subscription/claude-md"><img src="https://agentmods.dev/badge/instructions/vanssata/jetbrains-claude-subscription/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 | $0.00856 | $0.00856 |
| Opus 5 | $0.00428 | $0.00428 |
| Sonnet 5 | $0.00171 | $0.00171 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
jetbrains-claude-subscription 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 70 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.
Build
JAVA_HOME is not set in the shell and the only JDK on this machine is the JetBrains
Runtime shipped with PhpStorm. Always build with:
JAVA_HOME=/home/vanssa/.local/share/JetBrains/Toolbox/apps/phpstorm/jbr ./gradlew buildPlugin
# -> build/distributions/jetbrains-claude-subscription-<version>.zip
No Gradle toolchain is configured on purpose (build.gradle.kts explains why) — the build
compiles with whatever JDK Gradle runs on and targets JVM 21 bytecode.
ktlint runs through the kotlinter plugin — ./gradlew lintKotlin (same JAVA_HOME prefix),
or formatKotlin to apply fixes. Two rules are disabled in .editorconfig because the
existing code deliberately does otherwise; read the comment there before re-enabling them or
reformatting around them.
The build resolves the platform and the AI Assistant plugin from local installs via the
platformLocalPath and aiAssistantPluginPath properties in gradle.properties. Those are
absolute machine-specific paths; do not "fix" them to coordinates or downloads.
Verifying a change
There are no JVM tests — ./gradlew test compiles nothing meaningful and proves nothing.
Do not report a change as verified because Gradle succeeded.
Real verification is manual: build the zip, then
Settings → Plugins → ⚙ → Install Plugin from Disk…, restart, and check that
Claude Subscription appears in the AI chat agent picker with the Claude icon.
test/handshake.sh is the one automated check. It starts the ACP package outside the IDE and
asserts that the claude-ai-login auth method is offered — i.e. that the thing this plugin
exists for still works. Run it after any change to the package spec or node resolution.
Gotchas
- The pinned ACP package version lives in four places and they must not drift:
ClaudeAcpSettings.DEFAULT_PACKAGE_SPEC,test/handshake.sh, and two spots inREADME.md. Use/bump-acprather than editing by hand. - The
262.*build range is deliberate.AgentIconServiceis internal AI Assistant API, not a published contract. Do not widenuntilBuildto gain forward compatibility that has not been tested. ~/.jetbrains/acp.jsonis shared. Every write must merge — it holds other users' agents anddefault_mcp_settings. Never overwrite it, and keep the refuse-on-unparseable behaviour inAcpConfigFile.- The node
PATHentry is load-bearing.npx-cli.jsre-execs helpers through#!/usr/bin/env node, so an absolute node path alone fails. The path is also re-resolved on every startup because the IDE's fallback runtime path carries a version number. - The Kotlin stdlib is deliberately not bundled (
kotlin.stdlib.default.dependency=false); adding it back causes classloader conflicts at runtime.
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.
- 10d ago First seen · 70 lines · 856 tokens per session scan A 0adf942f606b
jetbrains-claude-subscription CLAUDE.md is an instructions file published in the GitHub repository vanssata/jetbrains-claude-subscription (5 stars, last pushed 1mo ago), licensed MIT. It adds 856 tokens to every session, about $0.0043 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.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.