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.
npx agentmods add instructions/fjlmcm/claude-code-statusline/claude-mdgit clone --depth 1 https://github.com/fjlmcm/claude-code-statuslineWrote 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.
[](https://agentmods.dev/instructions/fjlmcm/claude-code-statusline/claude-md)<a href="https://agentmods.dev/instructions/fjlmcm/claude-code-statusline/claude-md"><img src="https://agentmods.dev/badge/instructions/fjlmcm/claude-code-statusline/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00964 | $0.00964 |
| Opus 5 | $0.00482 | $0.00482 |
| Sonnet 5 | $0.00193 | $0.00193 |
| Haiku 4.5 | $0.00096 | $0.00096 |
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 4d 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.
- **setup.js** — Idempotent: copies scripts to `~/.claude/plugins/claude-code-statusline/`, sets `statusLine.command` in `~/.claude/settings.json` How it starts
The opening of the file, as written. The whole thing — 49 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
Claude Code statusline plugin — a Node.js CLI tool that renders a live status bar in Claude Code's terminal showing model info, git status, context usage, and real-time Anthropic API quota data. Supports 9 languages and two layout modes (expanded/compact).
Commands
- Run tests:
npm test(uses Jest) - Run a single test file:
npx jest tests/render.test.js - Manual install (for dev):
node ccsl-install.js - Manual uninstall:
node ccsl-uninstall.js - Test statusline output directly: pipe JSON to
node scripts/statusline.js
Architecture
The entry point is scripts/statusline.js. It reads JSON session data from stdin, assembles state from lib modules, and writes ANSI-formatted output to stdout.
Core modules (scripts/lib/)
- config.js — ANSI constants, path definitions (
~/.claude/files), config loading (file + env vars), credential reading (file or macOS Keychain), plan detection from OAuth subscription type - quota.js — Fetches quota from
api.anthropic.com/api/oauth/usagevia OAuth token; uses atomic file-based cache (usage_cache.json); stale cache triggers a detached background child process (--refresh-cacheflag); lock file prevents concurrent refresh spawns; 429 responses trigger exponential backoff (60s→120s→240s→300s cap) persisted to.backofffile - render.js —
renderExpanded(2-line) andrenderCompact(1-line) layouts; displays remaining quota percentage (100 - used); expanded mode shows 7d per-model breakdown inline (7d left:opus 80% sonnet 23%); color thresholds based on used%: green ≤50%, yellow ≤80%, red >80%; all spaces replaced with NBSP for terminal rendering - i18n.js —
STRINGS,TIME_FORMATS,DURATION_UNITSfor 9 locales (en/zh/ja/ko/fr/de/es/pt/ru);detectLang()checksCCSL_LANG→LANG/LC_ALL→Intl;fill()is a simple{key}template function - context.js — Calculates context window usage percentage from
used_percentageor token counts - git.js — Reads branch from
.git/HEADdirectly (supports worktrees via gitdir), runsgit status --porcelainandgit rev-listfor dirty/ahead/behind counts - transcript.js — Parses Claude Code JSONL transcript (tail 128KB) to count TodoWrite/TaskCreate/TaskUpdate operations for compact mode's task counter
- debug.js — Conditional logging to
~/.claude/statusline-debug.logwhenCCSL_DEBUG=1
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.
- 4d ago First seen · 49 lines · 964 tokens per session scan B 03003748da29
claude-code-statusline CLAUDE.md is an instructions file published in the GitHub repository fjlmcm/claude-code-statusline (3 stars, last pushed 5mo ago), licensed MIT. It adds 964 tokens to every session, about $0.0048 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 2026-08-31.
Other instructions, from other repositories
claude-code-quota CLAUDE.md
Instructions for aweussom/claude-code-quota, covering claude.md — working on claude-code-quota, what this is, deployment reality (drives most of the design), traps that have already bitten us and powershell: a bom-less utf-8 .ps1 is parsed as ansi by 5.1.
topgauge CLAUDE.md
Instructions for cwf818/topgauge, covering claude.md, what this is, commands, architecture and how it runs.
claude-scope CLAUDE.md
Instructions for YuriNachos/claude-scope, covering claude.md, quick commands, installation & default config, tech stack and architecture (overview).
cc-hud CLAUDE.md
Instructions for WaterTian/cc-hud, covering claude.md — cc-hud 项目指令, 项目概述, 技术栈, 项目结构 and 数据流.
simple-claude-code-statusline CLAUDE.md
Claude Code instructions for Postmodum37/simple-claude-code-statusline, covering claude.md, project overview, architecture, how the statusline works and building.
claude-code-mascot-statusline CLAUDE.md
Instructions for TeXmeijin/claude-code-mascot-statusline, covering claude.md, project summary, core design, 1. sprite-first pack format and 2. dual-source state detection.