What is examples CLAUDE.md?

Project instructions for a repository of example AI agents and MCP tools. MCP is a standard way for an AI agent to call external tools and services.

They guide work on agent and tool examples such as contact extraction, currency conversion, file organisation, image generation, reservations, Slack research, and weather services.

They explain the repository layout, project conventions, required checks, and sign-off rules so changes fit the individual examples.

examples CLAUDE.md — Instructions file by rossoctl

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/rossoctl/examples/claude-md

Clone the repo

git clone --depth 1 https://github.com/rossoctl/examples

Per session 1,136 This file is loaded in full into every session.

When invoked 1,136 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.01136	$0.01136
Opus 5	$0.00568	$0.00568
Sonnet 5	$0.00227	$0.00227
Haiku 4.5	$0.00114	$0.00114

Measured yesterday against content hash 5d036d0397ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

examples 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 yesterday.

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 · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Agent Examples

This file provides guidance for AI assistants working with this repository.

Overview

Community examples of AI agents (A2A protocol) and MCP tools for the Rossoctl platform. Each agent/tool is a self-contained Python project with its own pyproject.toml and Dockerfile.

Repository Structure

agent-examples/
├── a2a/                        # A2A protocol agents
│   ├── a2a_contact_extractor/  # Contact extraction agent
│   ├── a2a_currency_converter/ # Currency conversion agent
│   ├── cheerup_agent/          # Cheerup agent
│   ├── file_organizer/         # File organizer agent
│   ├── generic_agent/          # Generic agent template
│   ├── git_issue_agent/        # GitHub issue agent
│   ├── image_service/          # Image generation agent
│   ├── recipe_agent/           # Recipe agent
│   ├── reservation_service/    # Reservation agent
│   ├── simple_generalist/      # Simple generalist agent
│   ├── slack_researcher/       # Slack research agent
│   ├── trivia_agent/           # Trivia agent
│   └── weather_service/        # Weather agent
├── mcp/                        # MCP protocol tools
│   ├── cloud_storage_tool/     # Cloud storage tool
│   ├── flight_tool/            # Flight search tool
│   ├── github_tool/            # GitHub tool
│   ├── image_tool/             # Image tool
│   ├── movie_tool/             # Movie tool
│   ├── reservation_tool/       # Reservation tool
│   ├── shopping_tool/          # Shopping tool
│   ├── slack_tool/             # Slack tool
│   └── weather_tool/           # Weather tool
├── scripts/hooks/              # Git hooks
├── sample-environments.yaml    # K8s environment configs
└── pyproject.toml              # Root ruff config

Key Commands

Task	Command
Lint	`make lint`
Format	`make fmt`
Pre-commit install	`pre-commit install`

Code Style

Python 3.11+ across all agents/tools
Linting: ruff (config in root pyproject.toml)
Pre-commit hooks: pre-commit install
Each agent/tool has its own pyproject.toml for dependencies

Read the full file on GitHub · 133 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.

yesterday First seen · 133 lines · 1,136 tokens per session scan A 5d036d0397ba

Subscribe to this mod's changes

examples CLAUDE.md is an instructions file published in the GitHub repository rossoctl/examples (11 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,136 tokens to every session, about $0.0057 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 2026-08-30.

Creative and media Productivity Research a2a agentic-workflow ai-agents ai-tools mcp mcp-client

examples CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md - Agent Examples

Overview

Repository Structure

Key Commands

Code Style

What this file has done since we first saw it

Other instructions, from other repositories

autoclip CLAUDE.md

openai-compatible-imagegen AGENTS.md

excalimate CLAUDE.md

pilot CLAUDE.md

ai.tech-lead-stack AGENTS.md

comfyui_mcp AGENTS.md