agentmods.dev

BOB-Gemini-Free: Instructions file for Claude Code

CLAUDE.md

BOB-Gemini-Free CLAUDE.md is an instructions file for Claude Code from div197/BOB-Gemini-Free. It costs 11,179 tokens per session, scanned A, original, MIT.

A project instruction file for BOB Gemini Free, a Go gateway and desktop application that connects compatible AI services through several interfaces.

In plain words
What is it for?
Use it when developing BOB Gemini Free, including its gateway, desktop application, cross-platform builds, tests, and performance checks.
Why use it?
It tells coding agents how to build, test, format, benchmark, and diagnose the project without having to discover those procedures first.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is div197/BOB-Gemini-Free's own configuration. It tells Claude Code how to work on BOB-Gemini-Free itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything BOB-Gemini-Free configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/suru/Documents/BOB-Gemini-Free.

not rated 3repo changed 3d ago A scan 11,179 tokens original MIT
View source ↗ div197/BOB-Gemini-Free bob-gemini-free.abcsteps.com
Reuse

Borrowing it

Nothing to install: this file belongs to div197/BOB-Gemini-Free. 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/div197/BOB-Gemini-Free/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/div197/BOB-Gemini-Free

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.

agentmods badge for BOB-Gemini-Free CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/div197/bob-gemini-free/claude-md.svg)](https://agentmods.dev/instructions/div197/bob-gemini-free/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/div197/bob-gemini-free/claude-md"><img src="https://agentmods.dev/badge/instructions/div197/bob-gemini-free/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 11,179 This file is loaded in full into every session.
When invoked 11,179 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.11179 $0.11179
Opus 5 $0.05590 $0.05590
Sonnet 5 $0.02236 $0.02236
Haiku 4.5 $0.01118 $0.01118

Measured 3d ago against content hash b00ced88aaa2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

BOB-Gemini-Free 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 3d 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 · 458 lines

How it starts

The opening of the file, as written. The whole thing — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Claude Code Instructions for BOB Gemini Free

This repository contains BOB Gemini Free (Break Ordinary Boundaries) by ABCsteps (abcsteps.com) and Divyanshu Singh Chouhan (@div197).

1. Quick Build & Test Commands

# Build host binary
make build

# Cross-compile for all operating systems (macOS, Linux, Windows)
make dist

# Build Native Desktop App (Requires Wails CLI & CGO)
make desktop

# Run all tests across all packages
go test -count=1 ./...

# Run diagnostic integration test kit against local server
./bob-gemini-free --test --test-url http://127.0.0.1:9610

# Run concurrency benchmark
./bob-gemini-free --bench --bench-concurrency 3 --bench-requests 6

# Format Go code
gofmt -s -w .

2. Architecture & Design Principles

  • Pure Go Gateway: A Go single-binary gateway with bundled external Go dependencies; runtime size and RSS are environment/build dependent and must be measured.
  • Multi-protocol Gateway (implemented adapters; compatibility remains endpoint- and upstream-dependent):
    • POST /v1/chat/completions, POST /v1/responses, POST /v1/images/generations, GET /v1/models (OpenAI format)
    • POST /v1/messages (Anthropic format with full SSE lifecycle: message_start, content_block_delta, message_delta, message_stop)
    • GET /v1beta/models, POST /v1beta/models/{target} (Google Gemini format)
    • pkg/gateway (Embeddable Go library)
  • Zero-Config Cookie Auto-Discovery: Automatically checks ./cookie.txt and ~/.config/bob-gemini-free/cookie.txt on startup.
  • Multimodal Scotty Engine: Automatic image compression (internal/multimodal/compress.go) and Google Scotty resumable upload.
  • Observability Headers: Injects standard OpenAI processing headers (x-request-id, openai-processing-ms, openai-version); it does not advertise limits that are not enforced locally.

3. How Claude Code Uses BOB Gemini Free

Read the full file on GitHub · 458 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. 3d ago Changed · +22 tokens per session b00ced88aaa2
  2. 8d ago First seen · 458 lines · 11,157 tokens per session scan A ab8bfa2ad66b

Subscribe to this mod's changes

BOB-Gemini-Free CLAUDE.md is an instructions file published in the GitHub repository div197/BOB-Gemini-Free (3 stars, last pushed yesterday), licensed MIT. It adds 11,179 tokens to every session, about $0.0559 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.

GoMultimodalai-gatewaygeminiopenai-compatiblereverse-proxy
Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens