What is barbatos CLAUDE.md?

A repository-specific instruction file for Barbatos, documenting how to build and test the project, its Kotlin Multiplatform architecture, coding standards, and JSON-RPC rules.

Use it when working on Barbatos features, including its Ktor JSON-RPC server, Frida integration, native builds, and tests. TDD means writing tests alongside new code.

It gives an AI coding agent the project’s commands and conventions so proposed changes fit the existing codebase.

How victorlpgazolli/barbatos configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to victorlpgazolli/barbatos. 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/victorlpgazolli/barbatos/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/victorlpgazolli/barbatos

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/victorlpgazolli/barbatos/claude-md/github.svg)](https://agentmods.dev/instructions/victorlpgazolli/barbatos/claude-md)

Your own site

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

Per session 720 This file is loaded in full into every session.

When invoked 720 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	$0.00720	$0.00720
Opus 5.5	$0.00288	$0.00288
Sonnet 5.5	$0.00144	$0.00144
Haiku 4.5	$0.00072	$0.00072

Measured 1mo ago against content hash d946849cfdb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

barbatos 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 1mo 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 · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Developer Guide

Build & Test Commands

Download SDK: ./scripts/download_frida_devkit.sh [arch] (arch: arm64, aarch64, x86_64)
Compile (Native): ./gradlew linkReleaseExecutableMacosArm64
Run Tests (macOS): ./gradlew macosArm64Test
Run Tests (Linux): ./gradlew linuxX64Test
Full Validation: ./gradlew clean check
Run Binary: ./build/bin/macosArm64/releaseExecutable/barbatos.kexe

Technical Architecture

Multiplatform: Logic in src/commonMain, platform-specific entry and Frida bindings in src/unixMain.
API: Ktor-based HTTP server on port 8080. REST endpoints under /v0/api/* in RPC mode; JSON-RPC 2.0 over Streamable HTTP in MCP mode.
Frida Integration: Kotlin Native CInterop mapped to libfrida-core.a.
Mocking: MockFridaBridge used for all unit tests to simulate Frida behavior without devices.

Coding Standards

Language: All code and documentation must be in English.
TDD: New endpoints must have corresponding test cases in RpcHandlerTest.kt.
RPC Protocol:
- HTTP transport (barbatos rpc): one POST /v0/api/<snake_case> per method. The body is the params object and the response is the plain result — no jsonrpc/id envelope.
- Errors use real HTTP statuses: 400 malformed body, 404 unknown endpoint, 500 internal error, with a body of {"error":{"code","message"}}.
- Keep standard JSON-RPC error codes in the error body for traceability:
  - -32700: Parse error
  - -32601: Method not found
  - -32603: Internal error
- The MCP transport keeps JSON-RPC 2.0 semantics and forwards application-level errors as non-error MCP results.
Style:
- Use HandlerResult for robust HTTP response handling in the server.
- Prefer interface-driven design (FridaBridge).
- Use ShellResult for system command execution.
- No emojis in commit messages or code.

File Structure

src/commonMain/kotlin/rpc/: HTTP and MCP handler logic (models + dispatch).
src/commonMain/kotlin/bridge/: Bridge interfaces and mocks.
src/unixMain/kotlin/bridge/: Real Frida Core implementation.
src/commonMain/resources/: Frida JS agents.
scripts/: Automation for SDK management and CI.
web/openapi.yaml: Single source of truth for the API contract.

Read the full file on GitHub · 48 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.

1mo ago Changed · +2 lines · +123 tokens per session d946849cfdb8
2mo ago First seen · 46 lines · 597 tokens per session scan A 628ed55fcffb

Subscribe to this mod's changes

barbatos CLAUDE.md is an instructions file published in the GitHub repository victorlpgazolli/barbatos (11 stars, last pushed 1mo ago), licensed MIT. It adds 720 tokens to every session, about $0.0029 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 2026-08-31.

barbatos CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
barbatos CLAUDE.mdvictorlpgazolli/barbatos	Instructions file	11	1mo ago	MIT	A	720	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

barbatos: Instructions file for Claude Code