Ollama-Workbench: Instructions file for Claude Code

CLAUDE.md

Ollama-Workbench CLAUDE.md is an instructions file for Claude Code from marc-shade/Ollama-Workbench. It costs 2,035 tokens per session, scanned A, original, MIT.

Repository instructions for Ollama Workbench, a Streamlit app for managing and testing AI models, plus a small Flask server for browser-extension communication. They explain the project layout, commands, testing, linting, and setup.

In plain words
What is it for?
Use them when changing Ollama Workbench code, running its Streamlit app and Ollama server, executing tests, checking imports, linting, or setting up a new checkout.
Why use it?
They give a coding agent the project context and the exact commands needed to run, test, check, and set up the application.

Instructions file for Claude Code

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

This is marc-shade/Ollama-Workbench's own configuration. It tells Claude Code how to work on Ollama-Workbench 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 Ollama-Workbench configures →

Reuse

Borrowing it

Nothing to install: this file belongs to marc-shade/Ollama-Workbench. 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/marc-shade/Ollama-Workbench/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/marc-shade/Ollama-Workbench

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 Ollama-Workbench CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/marc-shade/ollama-workbench/claude-md.svg)](https://agentmods.dev/instructions/marc-shade/ollama-workbench/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/marc-shade/ollama-workbench/claude-md"><img src="https://agentmods.dev/badge/instructions/marc-shade/ollama-workbench/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,035 This file is loaded in full into every session.
When invoked 2,035 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.02035 $0.02035
Opus 5 $0.01018 $0.01018
Sonnet 5 $0.00407 $0.00407
Haiku 4.5 $0.00203 $0.00203

Measured 8d ago against content hash beea2fbb36c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Ollama-Workbench CLAUDE.md scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Ollama must be running at `http://localhost:11434`. Check: `curl -s http://localhost:11434/api/tags`
CLAUDE.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 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.

Project Overview

Ollama Workbench is a Streamlit-based platform for managing, testing, and interacting with AI models from Ollama and external providers (OpenAI, Groq, Mistral). It runs as a Streamlit app on port 8501 with a companion Flask API server on a dynamic port for Chrome extension communication.

Commands

# Run the app (recommended - handles Ollama server startup)
./start_workbench.sh

# Run manually
streamlit run main.py

# Run all tests
python scripts/run_all_tests.py

# Run pytest suite
python -m pytest tests/ -v
python -m pytest tests/test_chat_interfaces.py -v                    # specific file
python -m pytest tests/test_chat_interfaces.py::TestChatInterface -k "test_session"  # specific test

# Verify all package imports work
python scripts/test_imports.py

# Lint
ruff check .
flake8 .

# Setup from scratch
python scripts/setup_workbench.py

Package Structure

The codebase is organized into the ollama_workbench package with 8 sub-packages. main.py is the only Python file at the root — it's the Streamlit entry point.

main.py                          # Streamlit entry point + Flask API
ollama_workbench/
    providers/                   # AI provider API clients
        ollama_utils.py          #   Ollama (primary) - model mgmt, embeddings, monitoring
        openai_utils.py          #   OpenAI
        groq_utils.py            #   Groq
        mistral_utils.py         #   Mistral
        external_providers.py    #   Provider configuration UI
    chat/                        # Chat interfaces
        chat_interface.py        #   Base chat (token counting, RAG, agent prompts, CoT)
        enhanced_chat_interface.py  # Wraps chat_interface with Open WebUI styling
        multimodel_chat.py       #   Multi-model simultaneous chat
        multimodal_chat.py       #   Vision/image chat
        voice_interface.py       #   Voice chat (requires pyaudio)
        persona_chat.py          #   Persona group chat
        collaborative_workspace.py  # Collaborative workspace
        canvas.py                #   Document canvas for workspace
        voice_utils.py           #   Voice/TTS utilities
        tts_utils.py             #   Text-to-speech helpers
    workflows/                   # AI workflow orchestration
        build.py                 #   Autonomous software development
        research.py              #   Multi-source research automation
        brainstorm.py            #   AI brainstorming with multiple agents
        projects.py              #   AI-assisted project/task management
        nodes.py                 #   CEF visual workflow builder
        agents.py                #   Agent definitions
        info_brainstorm.py       #   Brainstorm info helpers
    knowledge/                   # Knowledge management & RAG
        simplified_rag.py        #   Enhanced RAG interface (active)
        enhanced_corpus.py       #   GraphRAG corpus management
        repo_docs.py             #   Repository analysis
        web_to_corpus.py         #   Web crawling to corpus
        search_libraries.py      #   Multi-engine web search
    models/                      # Model management & testing
        model_comparison.py      #   Response quality comparison
        model_tests.py           #   Performance benchmarks
        feature_test.py          #   Feature capability tests
        vision_comparison.py     #   Vision model comparison
        local_models.py          #   List/manage local models
        pull_model.py            #   Download new models
        show_model.py            #   Model details viewer
        remove_model.py          #   Model removal
        update_models.py         #   Batch model updates
        model_management.py      #   Management dashboard
        model_capabilities.py    #   Capability testing UI
        model_capability_registry.py  # Capability detection
        model_onboarding.py      #   Model onboarding tests
        test_visualization.py    #   Test result visualization
    server/                      # Server management
        server_configuration.py  #   Ollama server config
        server_monitoring.py     #   Resource monitoring
        performance_metrics.py   #   Performance tracking
        openai_compatibility.py  #   OpenAI-compatible API
    core/                        # Core infrastructure
        config.py                #   Application configuration
        session_utils.py         #   Session state management
        db_init.py               #   Database initialization
        error_handling.py        #   Error handling utilities
    ui/                          # UI components
        styles.py                #   Theming (apply_styles -> colors, theme)
        prompts.py               #   Prompt template management
        file_management.py       #   File browser/editor
        structured_output.py     #   JSON schema output UI
        tool_playground.py       #   Tool calling playground
        contextual_response.py   #   Contextual response testing
        welcome.py               #   Help/welcome page
        global_vrm_loader.py     #   VRM model loader
tests/                           # All test files
scripts/                         # Standalone utility scripts
persona_lab/                     # Persona generation lab
observability/                   # Optional Opik integration
tts_server/                      # Standalone TTS Flask server
prompts/                         # JSON prompt templates

Read the full file on GitHub · 173 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. 8d ago First seen · 173 lines · 2,035 tokens per session scan A beea2fbb36c5

Subscribe to this mod's changes

Ollama-Workbench CLAUDE.md is an instructions file published in the GitHub repository marc-shade/Ollama-Workbench (50 stars, last pushed 1mo ago), licensed MIT. It adds 2,035 tokens to every session, about $0.0102 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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