pre-usage-plugin: Instructions file for Claude Code

CLAUDE.md

pre-usage-plugin CLAUDE.md is an instructions file for Claude Code from Laotree/pre-usage-plugin. It costs 2,020 tokens per session, scanned B, original, MIT.

Repository instructions for the pre-usage-plugin, including its Rust commands, installation process, architecture, and Claude Code hook flow.

In plain words
What is it for?
Use it when changing or checking the pre-usage-plugin, including building it, running tests, formatting code, or simulating its prompt hook.
Why use it?
It gives coding agents one place to learn how the plug-in is built, installed, tested, and connected to Claude Code.

Instructions file for Claude Code

Written for Claude Code: UserPromptSubmit hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is Laotree/pre-usage-plugin's own configuration. It tells Claude Code how to work on pre-usage-plugin 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 pre-usage-plugin configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Laotree/pre-usage-plugin. 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/Laotree/pre-usage-plugin/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Laotree/pre-usage-plugin

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 pre-usage-plugin CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/laotree/pre-usage-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/laotree/pre-usage-plugin/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,020 This file is loaded in full into every session.
When invoked 2,020 The same file — it is already loaded in full.
Security scan B 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 $0.02020 $0.02020
Opus 5.5 $0.00808 $0.00808
Sonnet 5.5 $0.00404 $0.00404
Haiku 4.5 $0.00202 $0.00202

Measured 2mo ago against content hash f543552504a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

pre-usage-plugin CLAUDE.md scanned grade B 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`install.sh` registers it as a `UserPromptSubmit` hook in `~/.claude/settings.json`:
CLAUDE.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 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.

Commands

cargo build --release          # build the binary
cargo clippy                   # lint
cargo fmt                      # format
cargo test                     # run tests
./install.sh                   # build + install binary + register hook in settings.json

To test the binary directly (simulate a UserPromptSubmit hook call):

echo '{"prompt":"hello world","transcript_path":""}' \
  | ./target/release/pre-usage; echo "exit: $?"

Architecture

pre-usage is a Rust binary installed at ~/.claude/plugins/pre-usage.
install.sh registers it as a UserPromptSubmit hook in ~/.claude/settings.json:

{
  "hooks": {
    "UserPromptSubmit": [
      {
        "hooks": [
          { "type": "command", "command": "/Users/<you>/.claude/plugins/pre-usage" }
        ]
      }
    ]
  }
}

Claude Code calls the binary before every prompt is sent. The binary reads hook JSON from stdin, estimates token usage, and either exits 0 (proceed) or 2 (block).

Flow

UserPromptSubmit
      │
      ▼
  main.rs  ──reads stdin──▶  estimator.rs
                                  │
                          ┌───────┴────────┐
                          │                │
                   read session        estimate new
                   JSONL logs          prompt tokens
                   (accumulated        (content bytes ÷ 4)
                    session tokens)
                          │                │
                          └───────┬────────┘
                                  │
                            total_estimate
                                  │
                    ┌─────────────┴──────────────┐
                    │                            │
             ≤ threshold                   > threshold
                    │                            │
                exit 0                      ui.rs prompt
            (silent pass)              "[S]end  [C]ancel"
                                             │       │
                                           exit 0  exit 2

Read the full file on GitHub · 253 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 · 253 lines · 2,020 tokens per session scan B f543552504a2

Subscribe to this mod's changes

pre-usage-plugin CLAUDE.md is an instructions file published in the GitHub repository Laotree/pre-usage-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 2,020 tokens to every session, about $0.0081 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

pre-usage-plugin CLAUDE.md compared with instructions from other repositories

pre-usage-plugin CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pre-usage-plugin CLAUDE.mdLaotree/pre-usage-pluginInstructions file25mo agoMITB2,020Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, 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