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.
npx agentmods add instructions/marimerllc/rockbot/claude-mdgit clone --depth 1 https://github.com/MarimerLLC/rockbotWhat 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 | $0.00965 | $0.00965 |
| Opus 5 | $0.00483 | $0.00483 |
| Sonnet 5 | $0.00193 | $0.00193 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
rockbot 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.
How it starts
The opening of the file, as written. The whole thing — 75 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 & Test Commands
# Build
dotnet build RockBot.slnx
# Run all tests (unit only, no RabbitMQ needed)
dotnet test RockBot.slnx
# Run all tests including integration tests (requires RabbitMQ)
ROCKBOT_RABBITMQ_HOST=localhost dotnet test RockBot.slnx
# Run a single test by fully qualified name
dotnet test RockBot.slnx --filter "FullyQualifiedName~MessageEnvelopeTests.Create_SetsDefaults"
# Run tests by category/class
dotnet test RockBot.slnx --filter "ClassName~RabbitMqIntegrationTests"
Architecture
RockBot is an event-driven autonomous agent framework built on .NET 10. It replaces traditional game-loop agent patterns with a message-based, decoupled swarm architecture where agents communicate exclusively via a message bus.
Core design principle: "Nothing trusts the LLM." Agents run in separate processes with no shared memory, communicating only through messages. This provides process isolation so LLM-generated code cannot access the host directly.
Project Structure
src/RockBot.Messaging.Abstractions/— Provider-agnostic messaging contracts (IMessagePublisher,IMessageSubscriber,MessageEnvelope,MessageResult)src/RockBot.Messaging.RabbitMQ/— RabbitMQ implementation with topic exchange, dead-letter queues, and per-consumer channelstests/RockBot.Messaging.Tests/— MSTest unit tests + RabbitMQ integration tests (gated byROCKBOT_RABBITMQ_HOSTenv var)design/— Architecture docs, messaging design, security model, and open questions
Messaging Design
MessageEnvelope is a sealed record carrying: MessageId, MessageType, CorrelationId, ReplyTo, Source, Destination, Timestamp, Body (ReadOnlyMemory<byte>), and Headers. The body is raw bytes for transport agnosticism; convenience extensions (ToEnvelope<T>/GetPayload<T>) handle JSON serialization via System.Text.Json with camelCase policy.
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.
- 3d ago First seen · 75 lines · 965 tokens per session scan A d683a013d191
rockbot CLAUDE.md is an instructions file published in the GitHub repository MarimerLLC/rockbot (22 stars, last pushed 3d ago), licensed MIT. It adds 965 tokens to every session, about $0.0048 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.
Other instructions, from other repositories
AgentEval maf-updates.instructions.md
Instructions for detecting and adapting to Microsoft Agent Framework (MAF) breaking changes.
skunit copilot-instructions.md
Instructions for mehrandvd/skunit, covering working effectively, bootstrap, build, and test, code quality, demo projects and requirements and configuration.
maf-doctor copilot-instructions.md
Instructions for joslat/maf-doctor, covering maf 1.3.0 migration — auto-loaded constraints, maf 1.3.0 — constraints & breaking changes reference, hard constraints (never violate), fan-out / fan-in rules (silent failure risk) and key breaking changes.
maui performance-hotpaths.instructions.md
Instructions for dotnet/maui, covering performance-critical path rules, hot paths in maui, allocation avoidance, caching and invalidation and collection iteration.
mini-swe-agent copilot-instructions.md
Copilot instructions for SWE-agent/mini-swe-agent, covering style guide, test style, bad and good.
trpc-agent-go AGENTS.md
AGENTS.md instructions for trpc-group/trpc-agent-go, covering agents.md, project overview, engineering principles, go design conventions and implementation workflow.