What is token-savior CLAUDE.md?

Project instructions for Claude Code when working with Token Savior, a tool-routing setup that reduces the amount of tool information shown to the agent.

Use them to reproduce the documented benchmark setup and follow Token Savior's preferred tool workflow.

They define the recommended configuration and which tools to use for locating, reading, editing, auditing, and tracing code.

How Mibayy/token-savior configures Claude Code

About the project

Token Savior is an MCP server for AI coding agents that combines structural code navigation, persistent project memory, and Bash command rewriting. It is intended to help coding agents work through repositories with less token use and shorter execution times, and its catalogue add-ons configure or guide its use.

Mibayy/token-savior · 1,207 stars · on GitHub · mibayy.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to Mibayy/token-savior. 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/Mibayy/token-savior/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Mibayy/token-savior

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mibayy/token-savior/claude-md/github.svg)](https://agentmods.dev/instructions/mibayy/token-savior/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/mibayy/token-savior/claude-md"><img src="https://agentmods.dev/badge/instructions/mibayy/token-savior/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mibayy/token-savior/claude-md"><img src="https://agentmods.dev/badge/instructions/mibayy/token-savior/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,116 This file is loaded in full into every session.

When invoked 1,116 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01116	$0.01116
Opus 5.5	$0.00446	$0.00446
Sonnet 5.5	$0.00223	$0.00223
Haiku 4.5	$0.00112	$0.00112

Measured 2mo ago against content hash 5811bef579fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

token-savior 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 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.

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.

CLAUDE.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Token Savior — recommended config for Claude Code

This file is auto-discovered by Claude Code. It tells the agent how to use Token Savior efficiently. Drop this CLAUDE.md (or its contents) at the root of your own project to reproduce the 97.9% / −80% active-tokens result on tsbench.

Defaults the bench uses

TS_PROFILE=tiny_plus            # 15 tools, ~2.5 KT manifest
TS_CAPTURE_DISABLED=1           # skip read-side capture sandboxing

tiny_plus is the Pareto-optimal profile. It exposes exactly the 15 tools agents reach for after the first turn — locate, read, edit, audit, graph, git, and config — and hides the rest behind ts_search (Nomic embeddings on tool descriptions). Manifest math: tiny_plus ~2.5 KT vs lean ~7 KT vs full ~10 KT.

Tool routing (use these, not natives)

Goal	Tool	Replaces
Locate a symbol	`find_symbol(name)`	`grep -rn`
Read a function / class	`get_function_source(name)` / `get_class_source(name)`	`cat` + scroll
Read a range when you hold a line number (traceback, `grep -n`, compiler error)	`read_lines(file_path, start, end)`	`sed -n '105,150p'`, `head`, `tail`
One-shot context (loc + source + callers + deps)	`get_full_context(name)`	the whole chain
Search across project	`search_codebase(pattern)`	`grep` / `rg`
Discover any other tool	`ts_search(query)`	reading docs
Edit code (`.py`/`.ts`/`.tsx`/`.js`/`.jsx`)	`replace_symbol_source` / `insert_near_symbol`	`Edit` / `Write`
Add a model field (`.prisma`/`.py`/`.ts`)	`add_field_to_model`	hand edits
Move a symbol with import fixup	`move_symbol(name, target_file)`	copy-paste
Detect import cycles	`find_import_cycles`	manual reasoning
Detect duplicates	`find_semantic_duplicates(max_groups=30)`	manual review
Diff between refs	`detect_breaking_changes(ref="v1")`	`git diff` reading
Find dead code	`find_dead_code`	manual hunting
Audit config (orphans / secrets)	`analyze_config(checks=["orphans"])`	manual checks
Git status (structured)	`get_git_status`	`git status` parsing

Read the full file on GitHub · 80 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.

2mo ago First seen · 80 lines · 1,116 tokens per session scan A 5811bef579fd

Subscribe to this mod's changes

token-savior CLAUDE.md is an instructions file published in the GitHub repository Mibayy/token-savior (1,207 stars, last pushed 22d ago), licensed MIT. It adds 1,116 tokens to every session, about $0.0045 per session on Opus 5.5. 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 2026-08-30.

Building agents

token-savior CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
token-savior CLAUDE.mdMibayy/token-savior	Instructions file	1.2k	22d ago	MIT	A	1,116	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

token-savior: Instructions file for Claude Code