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/instantlyeasy/claudeware/claude-mdgit clone --depth 1 https://github.com/instantlyeasy/claudewareWhat 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 | $0.01757 | $0.01757 |
| Opus 5 | $0.00879 | $0.00879 |
| Sonnet 5 | $0.00351 | $0.00351 |
| Haiku 4.5 | $0.00176 | $0.00176 |
Grade A, and why
claudeware 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 2d 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Claudeware Project Guide
This document contains essential information for Claude Code instances working with the Claudeware project.
Project Overview
Claudeware is a zero-latency middleware system for Claude Code that enables query collection, analysis, and optimization through a plugin-based architecture. It works with both the Claude Code CLI and TypeScript SDK without any performance impact on output.
Key Features
- Zero-Latency Passthrough: CLI output is never delayed by processing
- Plugin System: Extensible middleware architecture with error isolation
- Query Collection: Automatic storage and categorization of all queries
- Token Optimization: Identifies opportunities to save tokens and optimize model usage
- SDK Integration: Works seamlessly with both CLI and TypeScript SDK
Architecture Summary
The wrapper uses a decoupled architecture to ensure zero latency:
Claude Code CLI → Process Manager → Stream Handler → Terminal (Direct Pipe)
↓
JSON Parser → Event Bus → Plugins → Database
Key Design Principle: Output is piped directly to terminal while parallel processing happens in the background. This guarantees zero latency impact.
Project Structure
claudeware/
├── src/ # Source code (mixed JS/TS)
│ ├── core/ # Core components (TypeScript)
│ │ ├── json-parser.ts
│ │ ├── process-manager.ts
│ │ └── stream-handler.ts
│ ├── plugins/ # Plugin system (TypeScript)
│ │ ├── event-bus.ts
│ │ ├── plugin-loader.ts
│ │ └── builtin/ # Built-in plugins
│ ├── database/ # Data layer
│ │ ├── sqlite-adapter.ts
│ │ └── batch-queue.ts
│ ├── adapters/ # Integration adapters
│ │ └── sdk-adapter.ts
│ ├── cli.js # CLI entry point (JavaScript)
│ ├── wrapper.js # Main wrapper orchestrator (JavaScript)
│ └── sdk.js # SDK integration (JavaScript)
├── docs/ # Comprehensive documentation
├── examples/ # Example plugins and usage
├── test/ # Test files
└── .dev/ # Development status documents
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.
- 2d ago First seen · 220 lines · 1,757 tokens per session scan A 413f3068e4e0
claudeware CLAUDE.md is an instructions file published in the GitHub repository instantlyeasy/claudeware (4 stars, last pushed 1y ago), licensed MIT. It adds 1,757 tokens to every session, about $0.0088 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.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.