What is claude-prune CLAUDE.md?

Repository instructions for Claude Code, an AI coding assistant, for a command-line tool that reduces the size of Claude Code session transcript files. They describe the project, commands, architecture, and local testing.

Maintaining and testing the claude-prune command-line tool, including pruning and restoring session files and running its automated tests.

They give the assistant the project context and the exact commands needed to install dependencies, test changes, build the tool, and try its commands locally.

How DannyAziz/claude-prune configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to DannyAziz/claude-prune. 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/DannyAziz/claude-prune/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/DannyAziz/claude-prune

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/dannyaziz/claude-prune/claude-md.svg)](https://agentmods.dev/instructions/dannyaziz/claude-prune/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/dannyaziz/claude-prune/claude-md"><img src="https://agentmods.dev/badge/instructions/dannyaziz/claude-prune/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 681 This file is loaded in full into every session.

When invoked 681 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	$0.00681	$0.00681
Opus 5	$0.00341	$0.00341
Sonnet 5	$0.00136	$0.00136
Haiku 4.5	$0.00068	$0.00068

Measured 8d ago against content hash 05d4acd7a1c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claude-prune 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 8d 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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 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

This is a CLI tool that prunes Claude Code session transcript files (.jsonl) to reduce context usage. The tool operates on session files stored in $CLAUDE_CONFIG_DIR/projects/{project-path-with-hyphens}/{sessionId}.jsonl (where $CLAUDE_CONFIG_DIR defaults to ~/.claude if not set).

Essential Commands

# Development
bun install                    # Install dependencies
bun test                      # Run all tests
bun test --watch              # Run tests in watch mode  
bun test --coverage           # Run tests with coverage
bun run build                 # Build for distribution

# Testing the CLI locally
bun run src/index.ts prune <sessionId> -k 10   # Test prune command
bun run src/index.ts restore <sessionId>       # Test restore command
./dist/index.js --help                         # Test built CLI

# Single test file
bunx vitest src/index.test.ts

Architecture

Core Logic: The pruneSessionLines() function (exported for testing) contains the main pruning algorithm that:

Always preserves the first line (session metadata/summary)
Finds assistant message indices and keeps everything from the Nth-to-last assistant message forward
Preserves all non-message lines (tool results, system diagnostics)
Cache Token Hack: Zeros out the last non-zero cache_read_input_tokens to reduce UI context percentage

Restore Logic: The findLatestBackup() function (exported for testing) handles backup file discovery:

Filters files by session ID pattern ({sessionId}.jsonl.{timestamp})
Filters out malformed timestamps (NaN values)
Sorts by timestamp and returns the most recent backup

Project Path Resolution: Claude Code stores projects using hyphenated absolute paths (e.g., /Users/alice/project becomes -Users-alice-project), handled by process.cwd().replace(/\//g, '-').

Backup Strategy: Creates backups in prune-backup/ subdirectory with format {sessionId}.jsonl.{timestamp} before modifications.

Read the full file on GitHub · 57 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.

8d ago First seen · 57 lines · 681 tokens per session scan A 05d4acd7a1c9

Subscribe to this mod's changes

claude-prune CLAUDE.md is an instructions file published in the GitHub repository DannyAziz/claude-prune (83 stars, last pushed 11mo ago), licensed MIT. It adds 681 tokens to every session, about $0.0034 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 2026-08-30.

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

claude-prune: Instructions file for Claude Code