Token reduction maximization: a real stack that cut Claude costs by 30x

AgentsView says Mars processed $1,530 worth of tokens last month.

The actual spend to date: $50. On a $100/month Claude Max subscription.

Three tools. Here's how.

Two numbers being measured:

AgentsView reads local session token counts and multiplies by Anthropic's published API pricing. It doesn't know you're on Claude Max — a flat subscription, no per-token billing. So $1,530 is the real usage value: what it would cost on pay-per-token API. The $50 is what it actually cost.

That gap has two causes: the subscription model, and a stack that compressed token usage before it ever hit the meter.

Layer 1: RTK (Rust Token Killer)

github.com/rtk-ai/rtk · brew install rtk

RTK sits between your terminal and Claude's context and filters noise. git status on a 280-file repo normally dumps ~3,000 tokens of file listings into context. RTK trims that to ~200. Same information, 15x smaller, on every shell operation, without thinking about it.

Layer 2: Graphify

github.com/safishamsi/graphify · pip install graphifyy

The heavy one. Graphify turns a codebase or document vault into a persistent knowledge graph — JSON and interactive HTML. Build it once, query it forever. Instead of Claude re-reading 10–15 files to answer a question, it traverses 3–5 nodes in a graph that already exists on disk.

One session. 16 Obsidian vaults, 4 production codebases:

[see attachment]

910x reduction means a corpus that used to cost 545,000 tokens to query now costs ~600. 🤯

It also finds connections that were never explicitly linked — concept clusters across files, architectural patterns that only become visible when everything is indexed at once.

Layer 3: Markdown Guard hook

This one doesn't save tokens. It keeps the agent safe.

Vaults are full of external content: captured links, scraped docs, research notes pulled from anywhere. A poisoned .md file can silently redirect an agent mid-session — change what it does next, what it writes, what it deletes. When that agent has write access to your systems, that's not theoretical.

The Markdown Guard is a PreToolUse hook that scans every .md file before Claude reads it and blocks injection attempts. One JSON entry in Claude Code settings.

Security is part of the stack, not an afterthought.

The actual math:

Before: Claude reads 12 files to answer one question. ~60,000 tokens. ~$0.18 at API rates. 😕

After: Claude queries the graph. ~400 tokens. ~$0.001. 👏

Multiply across every question in every session in a month.

AgentsView clocks $1,530 in theoretical API value. Claude Max covers it for $100/month flat — and $50 of that is still unspent.

The stack reduced how many tokens got consumed. The subscription eliminated the per-token cost on what remained.

You need both. One without the other leaves money on the table.

Setup:

RTK: brew install rtk + one hook config entry. Done.

Graphify: pip install graphifyy → graphify run in your project → graphify claude install to wire it to Claude Code.

Markdown Guard: one JSON entry in .claude/settings.json.