Isartor: Instructions file for Claude Code

CLAUDE.md

Isartor CLAUDE.md is an instructions file for Claude Code from isartor-ai/Isartor. It costs 2,383 tokens per session, scanned A, original, Apache-2.0.

A repository guide for Isartor, a Rust service that sits between coding tools and language models to handle some requests locally and forward others to cloud models.

In plain words
What is it for?
Use it when changing Isartor’s request handling, authentication, API compatibility, proxy, or tool-integration code.
Why use it?
It gives agents the project’s request flow and architectural rules, including where startup and middleware behavior are defined.

Instructions file for Claude Code

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

This is isartor-ai/Isartor's own configuration. It tells Claude Code how to work on Isartor 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 Isartor configures →

Reuse

Borrowing it

Nothing to install: this file belongs to isartor-ai/Isartor. 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/isartor-ai/Isartor/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/isartor-ai/Isartor

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 Isartor CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/isartor-ai/isartor/claude-md/github.svg)](https://agentmods.dev/instructions/isartor-ai/isartor/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/isartor-ai/isartor/claude-md"><img src="https://agentmods.dev/badge/instructions/isartor-ai/isartor/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Isartor CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/isartor-ai/isartor/claude-md"><img src="https://agentmods.dev/badge/instructions/isartor-ai/isartor/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,383 This file is loaded in full into every session.
When invoked 2,383 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 $0.02383 $0.02383
Opus 5 $0.01192 $0.01192
Sonnet 5 $0.00477 $0.00477
Haiku 4.5 $0.00238 $0.00238

Measured 10d ago against content hash ac3d4d3af30c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

Isartor 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 10d 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.

curl http://localhost:8080/health
CLAUDE.md · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Isartor — Claude Code Guide

This file helps Claude Code understand the Isartor codebase quickly and make safe changes.

What Isartor is

Isartor is a pure-Rust LLM gateway / prompt firewall. It sits in front of coding tools and SDKs, tries to resolve requests locally, and only sends the hard ones to a cloud model.

Main request flow:

L1a exact cache -> L1b semantic cache -> L2 SLM triage -> L3 cloud provider

Supported client surfaces:

  • Native API: POST /api/chat
  • OpenAI-compatible API: POST /v1/chat/completions
  • Anthropic-compatible API: POST /v1/messages
  • Gemini-compatible API: POST /v1beta/models/*:generateContent
  • Cursor / Kiro compatibility on /v1/chat/completions via header-based format detection
  • CONNECT proxy for Copilot-style traffic: src/proxy/connect.rs
  • MCP server for tool integrations: isartor mcp

What matters most architecturally

1. src/main.rs is the real boot sequence

src/main.rs loads config, initializes telemetry, builds shared AppState, wires the Axum router, and optionally starts the CONNECT proxy.

Authenticated routes are wired in src/main.rs and intentionally go through the full middleware stack.

2. Middleware ordering is critical

The intended request execution order is:

body buffer -> monitoring -> auth -> cache -> slm triage -> context optimizer -> handler

Axum middleware wraps inside-out, so the last .layer(...) added runs first. Do not reorder casually.

3. BufferedBody is required

src/middleware/body_buffer.rs reads the request body once and stores a clone in request extensions. Downstream layers are expected to read from BufferedBody, not consume the stream directly.

This is especially important for:

  • cache key extraction
  • Anthropic/OpenAI compatibility handlers
  • monitoring
  • retries and middleware composition

4. AppState is the runtime wiring hub

src/state.rs owns:

  • the shared reqwest::Client
  • the L1 exact cache
  • the semantic vector cache
  • the in-process text embedder
  • the configured L3 provider via AppLlmAgent
  • the SLM client

Read the full file on GitHub · 307 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. 10d ago First seen · 307 lines · 2,383 tokens per session scan A ac3d4d3af30c

Subscribe to this mod's changes

Isartor CLAUDE.md is an instructions file published in the GitHub repository isartor-ai/Isartor (21 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 2,383 tokens to every session, about $0.0119 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

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

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