claude-code-statusline CLAUDE.md

claude-code-statusline CLAUDE.md is an instructions file for coding agents from glauberlima/claude-code-statusline. It costs 2,776 tokens per session, scanned B, original, MIT.

Project instructions for developing and testing a Rust command-line status display for Claude Code.

In plain words
What is it for?
Build the statusline binary, run unit or integration tests, perform manual checks, and understand which status details it displays.
Why use it?
They give an unfamiliar contributor the repository's expected commands, structure, and behavior to follow.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/glauberlima/claude-code-statusline/claude-md
Clone the repo
git clone --depth 1 https://github.com/glauberlima/claude-code-statusline

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 claude-code-statusline CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/glauberlima/claude-code-statusline/claude-md.svg)](https://agentmods.dev/instructions/glauberlima/claude-code-statusline/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/glauberlima/claude-code-statusline/claude-md"><img src="https://agentmods.dev/badge/instructions/glauberlima/claude-code-statusline/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,776 This file is loaded in full into every session.
When invoked 2,776 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
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 $0.02776 $0.02776
Opus 5 $0.01388 $0.01388
Sonnet 5 $0.00555 $0.00555
Haiku 4.5 $0.00278 $0.00278

Measured 5d ago against content hash 0dd9c3e0d78c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

claude-code-statusline 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 5d 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.

| `src/configure.rs` | `--configure-settings <settings_path> <command_path>` — reads/merges/writes `~/.claude/settings.json` atomically |
CLAUDE.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 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

Rust binary statusline for Claude Code CLI displaying (in order):

  • Directory (📁)
  • Git branch (🌿) when in a Git repository
  • File changes (✏️) when present
  • Model name (🤖)
  • Context usage visualization with progress bar (📊)
  • Cost tracking (💰) when present and enabled

Primary file: src/main.rs Language: Rust 1.96, edition 2024 Binary name: statusline

Development Commands

Testing

# Run all tests (unit + integration)
cargo test

# Run only unit tests (inline #[cfg(test)] in src/*.rs)
cargo test --bins

# Run integration tests (builds the binary first)
cargo test --test integration

# Manual testing
echo '{"model":{"display_name":"Test"},"workspace":{"current_dir":"/tmp"},"context_window":{"context_window_size":200000,"remaining_percentage":72,"current_usage":{"input_tokens":1000,"output_tokens":0,"cache_creation_input_tokens":0,"cache_read_input_tokens":0}},"cost":{"total_cost_usd":0.42}}' | cargo run --quiet

Building

# Dev build
cargo build

# Release build
cargo build --release

# Dev install (build debug binary and copy manually)
cargo build && cp target/debug/statusline ~/.claude/statusline

Linting

cargo clippy --all-targets -- -D warnings

Architecture

Data Flow

JSON stdin → input.rs (parse) → config.rs (load TOML) → git.rs (git status) → components.rs (build) → render.rs (assemble) → stdout

Module Map

Module Responsibility
src/main.rs Entry point: --print-defaults, --version, --configure-settings flags or parse→build→render pipeline
src/configure.rs --configure-settings <settings_path> <command_path> — reads/merges/writes ~/.claude/settings.json atomically
src/input.rs JSON parsing via serde_json; validate_directory() for security
src/config.rs TOML config loading; BarStyle/Language/Theme enums with fallback warnings; print_defaults()
src/git.rs Single git status --porcelain=v2 --branch --untracked-files=all call; parse_porcelain_v2()
src/components.rs All component builders (build_model, build_directory, build_git, build_files, build_context, build_cost), each taking a &Palette; build_all() orchestrator
src/render.rs ANSI color constants, Palette/build_palette() (theme → semantic colors), BAR_FILLED/BAR_EMPTY/BAR_WIDTH, assemble()
src/debug_log.rs Debug-only (#[cfg(debug_assertions)]): appends raw stdin JSON to ~/.claude/statusline-debug.log for troubleshooting
tests/integration.rs End-to-end tests spawning the compiled binary with fixture JSON

Read the full file on GitHub · 215 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. 5d ago First seen · 215 lines · 2,776 tokens per session scan B 0dd9c3e0d78c

Subscribe to this mod's changes

claude-code-statusline CLAUDE.md is an instructions file published in the GitHub repository glauberlima/claude-code-statusline (49 stars, last pushed 16d ago), licensed MIT. It adds 2,776 tokens to every session, about $0.0139 per session on Opus 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 2026-08-30.