autocache: Instructions file for Claude Code

CLAUDE.md

autocache CLAUDE.md is an instructions file for Claude Code from montevive/autocache. It costs 1,954 tokens per session, scanned A, original, MIT.

Development guidance for Autocache, a proxy server that sits between applications and the Anthropic Claude API and adds cache-control information to requests. Request caching can avoid sending repeated context to the API.

In plain words
What is it for?
Use it when working on cache injection, proxy configuration, API testing, health checks, metrics, or the Go test suite.
Why use it?
It explains how to build, run, configure, test, and inspect the proxy during development.

Instructions file for Claude Code

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

This is montevive/autocache's own configuration. It tells Claude Code how to work on autocache 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 autocache configures →

Reuse

Borrowing it

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

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 autocache CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/montevive/autocache/claude-md/github.svg)](https://agentmods.dev/instructions/montevive/autocache/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/montevive/autocache/claude-md"><img src="https://agentmods.dev/badge/instructions/montevive/autocache/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 autocache CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/montevive/autocache/claude-md"><img src="https://agentmods.dev/badge/instructions/montevive/autocache/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,954 This file is loaded in full into every session.
When invoked 1,954 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 $0.01954 $0.01954
Opus 5.5 $0.00782 $0.00782
Sonnet 5.5 $0.00391 $0.00391
Haiku 4.5 $0.00195 $0.00195

Measured 2mo ago against content hash 4b5e2a6051e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

autocache 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 2mo 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 · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 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.

Project Overview

Autocache is an intelligent proxy server for the Anthropic Claude API that automatically injects cache-control fields into requests to reduce costs by up to 90% and latency by up to 85%. It acts as a drop-in replacement proxy that intelligently places cache breakpoints based on token analysis and ROI calculations.

Build and Test Commands

Build

go build -o autocache ./cmd/autocache

Run

# Start with defaults
./autocache

# With custom configuration
CACHE_STRATEGY=aggressive LOG_LEVEL=debug ./autocache

# Using Docker
docker-compose up -d

Run Tests

# Run all unit tests
go test ./... -v

# Run unit tests with coverage
go test ./... -cover

# Run real API tests (requires ANTHROPIC_API_KEY in .env)
./test_real.sh

# Run specific test files
go test -v -run TestCacheInjector

Development

# Run with debug logging
LOG_LEVEL=debug ./autocache

# Run with specific strategy
CACHE_STRATEGY=conservative ./autocache

# Check health
curl http://localhost:8080/health

# Check metrics
curl http://localhost:8080/metrics

Architecture

Project Structure

autocache-gh/
├── cmd/
│   └── autocache/
│       └── main.go                    # Entry point
├── internal/
│   ├── types/                         # Shared types and models
│   │   └── models.go
│   ├── config/                        # Configuration
│   │   └── config.go
│   ├── tokenizer/                     # Token counting
│   │   ├── tokenizer.go              # Interface + heuristic impl
│   │   ├── offline_tokenizer.go      # Embedded tokenizer
│   │   ├── real_tokenizer.go         # API-based tokenizer
│   │   └── anthropic_real_tokenizer.go
│   ├── pricing/                       # Cost calculations
│   │   └── pricing.go
│   ├── client/                        # Anthropic API client
│   │   └── anthropic.go
│   ├── cache/                         # Cache injection logic
│   │   └── injector.go
│   └── server/                        # HTTP server
│       └── handler.go
└── test_fixtures.go                   # Test helpers

Read the full file on GitHub · 222 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. 2mo ago First seen · 222 lines · 1,954 tokens per session scan A 4b5e2a6051e8

Subscribe to this mod's changes

autocache CLAUDE.md is an instructions file published in the GitHub repository montevive/autocache (178 stars, last pushed 9mo ago), licensed MIT. It adds 1,954 tokens to every session, about $0.0078 per session on Opus 5.5. 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

autocache CLAUDE.md compared with instructions from other repositories

autocache CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
autocache CLAUDE.mdmontevive/autocacheInstructions file1789mo agoMITA1,954Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode