What is ClaudeTokenSAP CLAUDE.md?

A set of project instructions for building a Claude Code plugin that reduces the amount of text sent through a coding session while keeping the user in control.

Use it to specify the plugin files, first-run questions, project setup, and handling rules for images, videos, logs, and model preferences.

It defines how to keep startup context small and avoid processing optional files unless the user wants them included.

How satyamamarpandey/ClaudeTokenSAP configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to satyamamarpandey/ClaudeTokenSAP. 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/satyamamarpandey/ClaudeTokenSAP/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/satyamamarpandey/ClaudeTokenSAP

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/satyamamarpandey/claudetokensap/claude-md/github.svg)](https://agentmods.dev/instructions/satyamamarpandey/claudetokensap/claude-md)

Your own site

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

Per session 1,067 This file is loaded in full into every session.

When invoked 1,067 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	$0.01067	$0.01067
Opus 5	$0.00534	$0.00534
Sonnet 5	$0.00213	$0.00213
Haiku 4.5	$0.00107	$0.00107

Measured 11d ago against content hash 2a80f5635fe0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ClaudeTokenSAP 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 11d 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 · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Token Optimizer Plugin - Build Rules

Goal

Build a production-ready Claude Code plugin that minimizes token usage across a session while preserving user control.

Primary objectives

Create a Claude Code plugin, not a skill-only solution.
Keep startup context very small.
Automatically set up the project on first run.
Ask the user a few onboarding questions only once, then generate a short project-specific CLAUDE.md.
Use lightweight processing first whenever possible.
Respect user control for optional files like images, videos, and logs.

Plugin requirements

The plugin must include:

.claude-plugin/plugin.json
.claude/settings.json
.claude/CLAUDE.md
.claude/skills/token-optimizer/SKILL.md
.claude/skills/token-optimizer/resources/ignore_rules.json
hooks/instructions_loaded.py
hooks/prompt_preprocess.py
README.md

First-run onboarding

On the first session only:

Detect whether project onboarding is incomplete.
Ask the user a few short questions:
- What are you building?
- Who are the target users?
- Which platforms are you targeting?
- Which Claude model do you expect to use most?
- Any important constraints or coding preferences?
Use the answers to generate a very short project-specific CLAUDE.md.
Save onboarding state so the questions are not asked again unless reset.

CLAUDE.md generation rules

Generated CLAUDE.md must be short and high-signal. It should include only:

what is being built
target users
platforms
preferred model strategy
key constraints
instruction to keep context usage low

Do not generate a long CLAUDE.md.

settings.json rules

Use .claude/settings.json to define:

deny rules for bulky folders and irrelevant generated content
ask rules for files the user may still want to include

Deny by default

Prefer denying:

node_modules
dist
build
.next
.cache
coverage
archives and other bulky generated artifacts

Read the full file on GitHub · 169 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.

11d ago First seen · 169 lines · 1,067 tokens per session scan A 2a80f5635fe0

Subscribe to this mod's changes

ClaudeTokenSAP CLAUDE.md is an instructions file published in the GitHub repository satyamamarpandey/ClaudeTokenSAP (3 stars, last pushed 5mo ago), licensed MIT. It adds 1,067 tokens to every session, about $0.0053 per session on Opus 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 2026-08-31.

Claude Code LLM automation claude-code-plugin claude-code-plugins developer-tools

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

ClaudeTokenSAP: Instructions file for Claude Code