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/osodevops/kafka-backup/claude-mdgit clone --depth 1 https://github.com/osodevops/kafka-backupWrote 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.
[](https://agentmods.dev/instructions/osodevops/kafka-backup/claude-md)<a href="https://agentmods.dev/instructions/osodevops/kafka-backup/claude-md"><img src="https://agentmods.dev/badge/instructions/osodevops/kafka-backup/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.03581 | $0.03581 |
| Opus 5 | $0.01791 | $0.01791 |
| Sonnet 5 | $0.00716 | $0.00716 |
| Haiku 4.5 | $0.00358 | $0.00358 |
Grade A, and why
kafka-backup 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 — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Development Guide for OSO Kafka Backup & Restore
This document provides context for AI-assisted development on this project.
Project Overview
OSO Kafka Backup & Restore is a high-performance, production-grade tool written in Rust for backing up and restoring Apache Kafka topics to cloud storage or local filesystem. It supports point-in-time recovery (PITR) with millisecond precision and handles consumer group offset recovery across different clusters.
Key Problems Solved
- Durable backup of Kafka topics to S3, Azure Blob, GCS, or local filesystem
- Disaster recovery with exact data fidelity
- Point-in-time restore (PITR) with millisecond precision
- Consumer group offset recovery across different clusters (offset space discontinuity problem)
- Deployment-agnostic: works on bare metal, VM, Docker, Kubernetes
Repository Structure
kafka-backup/
├── Cargo.toml # Workspace root
├── crates/
│ ├── kafka-backup-core/ # Core library (no K8s dependencies)
│ │ └── src/
│ │ ├── lib.rs # Module exports
│ │ ├── backup/ # Backup engine
│ │ ├── restore/ # Restore engine + offset handling
│ │ ├── kafka/ # Kafka protocol client
│ │ ├── storage/ # Multi-backend storage abstraction
│ │ ├── segment/ # Record batching & serialization
│ │ ├── offset_store/ # SQLite-based offset tracking
│ │ ├── config.rs # Configuration structures
│ │ ├── manifest.rs # Backup manifest & reports
│ │ ├── compression.rs # Compression algorithms
│ │ ├── error.rs # Error types
│ │ ├── circuit_breaker.rs
│ │ ├── health.rs
│ │ └── metrics/ # Prometheus metrics
│ └── kafka-backup-cli/ # Binary CLI wrapper
│ └── src/
│ ├── main.rs # CLI entry point
│ └── commands/ # Command implementations
├── config/ # Config templates
└── docs/ # Comprehensive documentation
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 · 429 lines · 3,581 tokens per session scan A c739da545c81
kafka-backup CLAUDE.md is an instructions file published in the GitHub repository osodevops/kafka-backup (42 stars, last pushed 4d ago), licensed MIT. It adds 3,581 tokens to every session, about $0.0179 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
jikkou AGENTS.md
Instructions for streamthoughts/jikkou, covering agents.md - development guidelines for ai coding agents, project overview, project structure, build, test, and lint commands and build commands.
klag CLAUDE.md
Instructions for themoah/klag, covering claude.md, project overview, build commands, graalvm native image (startup/memory optimized) and architecture.
jikkou CLAUDE.md
Instructions for streamthoughts/jikkou, a project described as: The Open source Resource as Code framework for Apache Kafka. Jikkou helps you implement GitOps for Kafka at scale!
git-proxy AGENTS.md
Instructions for finos/git-proxy, covering agents.md — gitproxy, project overview, build & run, build and run unit tests.
agent-skills AGENTS.md
AGENTS.md instructions for fluxcd/agent-skills, covering agent instructions, repository layout, working on existing skills, running skill evals and adding a new skill.
bex CLAUDE.md
Instructions for bex-co/bex, covering claude.md, repo map, commands, local cluster workflow and environment variables.