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/montevive/autocache/claude-mdgit clone --depth 1 https://github.com/montevive/autocacheWrote 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/montevive/autocache/claude-md)<a href="https://agentmods.dev/instructions/montevive/autocache/claude-md"><img src="https://agentmods.dev/badge/instructions/montevive/autocache/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 | $0.01954 | $0.01954 |
| Opus 5 | $0.00977 | $0.00977 |
| Sonnet 5 | $0.00391 | $0.00391 |
| Haiku 4.5 | $0.00195 | $0.00195 |
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 4d 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 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
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.
- 4d ago First seen · 222 lines · 1,954 tokens per session scan A 4b5e2a6051e8
autocache CLAUDE.md is an instructions file published in the GitHub repository montevive/autocache (170 stars, last pushed 7mo ago), licensed MIT. It adds 1,954 tokens to every session, about $0.0098 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.
Other instructions, from other repositories
selfhost-ai CLAUDE.md
Claude Code instructions for kossakovsky/selfhost-ai, covering claude.md, project overview, core architecture, key files and installation flow.
mockserver-monorepo AGENTS.md
AGENTS.md instructions for mock-server/mockserver-monorepo, covering mockserver — agent instructions, instruction priority, project overview, local development environment and project documentation.
n8n-skills CLAUDE.md
Claude Code instructions for czlonkowski/n8n-skills, covering claude.md, project overview, repository structure, the 14 skills and 1. n8n expression syntax.
plano CLAUDE.md
Instructions for katanemo/plano, covering claude.md, build & test commands, rust — wasm plugins (must target wasm32-wasip1), rust — brightstaff binary (native target) and rust — tests, format, lint.
GreenTunnel CLAUDE.md
Claude Code instructions for SadeghHayeri/GreenTunnel, covering greentunnel v3, commands, running the cli, ⚠️ npm run dev changes your real system proxy and layout.
claude-tap AGENTS.md
Instructions for liaohch3/claude-tap, covering maintainer automation notes, agents 索引, documentation boundary, review guidelines and pre-commit hook.