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/postmodum37/simple-claude-code-statusline/claude-mdgit clone --depth 1 https://github.com/Postmodum37/simple-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/postmodum37/simple-claude-code-statusline/claude-md)<a href="https://agentmods.dev/instructions/postmodum37/simple-claude-code-statusline/claude-md"><img src="https://agentmods.dev/badge/instructions/postmodum37/simple-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 | $0.06887 | $0.06887 |
| Opus 5 | $0.03444 | $0.03444 |
| Sonnet 5 | $0.01377 | $0.01377 |
| Haiku 4.5 | $0.00689 | $0.00689 |
Grade B, and why
simple-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.
- `commands/setup.md` - Command that configures `~/.claude/settings.json` How it starts
The opening of the file, as written. The whole thing — 303 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 Claude Code plugin that provides a custom two-line statusline. It's implemented as cross-compiled Go binaries dispatched via a thin bash shim (bin/statusline.sh).
Architecture
This repo serves as both a marketplace and a plugin:
.claude-plugin/marketplace.json- Makes this repo a Claude Code marketplace.claude-plugin/plugin.json- Plugin manifestsrc/- Go source files (stdin parsing, rendering, git, usage API, formatting)bin/statusline.sh- Bash shim that detects OS/arch and execs the correct binarybin/{os}-{arch}/statusline- Cross-compiled Go binaries (darwin/linux, amd64/arm64)Makefile- Build targets:build(cross-compile all),test,cleancommands/setup.md- Command that configures~/.claude/settings.jsonhooks/- SessionStart hook that reminds users to run setup if not configured
When installed, the plugin runs from ${CLAUDE_PLUGIN_ROOT}/bin/statusline.sh (the plugin cache directory), which dispatches to the platform-appropriate binary.
How the Statusline Works
Claude Code pipes JSON to the binary via stdin containing:
model.id/model.display_name- Current modelcwd/workspace.project_dir- Current/project directoriescontext_window.*- Token usage and context sizesession_id- For session duration trackingcost.total_lines_added/cost.total_lines_removed- Session-cumulative lines changedagent.name- Agent name (when using--agentflag)worktree.*- Worktree metadata (only present in--worktreesessions, since v2.1.69)rate_limits.{five_hour,seven_day}- Rate limit windows (since v2.1.80)effort.level- Reasoning effort:low|medium|high|xhigh|max(since v2.1.119; docs no longer listauto— ultracode reports asxhigh)thinking.enabled- Whether extended thinking is on (since v2.1.119)pr.{number,url,review_state}- Open PR for the current branch (since v2.1.145; absent until a PR is found)workspace.repo.{host,owner,name}- Repo identity from theoriginremote (since v2.1.145)exceeds_200k_tokens- Whether the most recent API response exceeded 200k tokens
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 · 303 lines · 6,887 tokens per session scan B 9da3415f6715
simple-claude-code-statusline CLAUDE.md is an instructions file published in the GitHub repository Postmodum37/simple-claude-code-statusline (5 stars, last pushed 1mo ago), licensed MIT. It adds 6,887 tokens to every session, about $0.0344 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-scope CLAUDE.md
Instructions for YuriNachos/claude-scope, covering claude.md, quick commands, installation & default config, tech stack and architecture (overview).
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.
claude-code-mascot-statusline AGENTS.md
Instructions for TeXmeijin/claude-code-mascot-statusline, covering agents.md, primary goal, what matters here, architecture and non-negotiable product rules.
claude-code-statusline CLAUDE.md
Instructions for glauberlima/claude-code-statusline, covering claude.md, project overview, development commands, testing and run all tests (unit + integration).
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.
fleetline CLAUDE.md
Instructions for ClaudeTool/fleetline, covering fleetline — project context for claude, what this is, file map, non-obvious things you need to know before editing and open todos for whoever picks this up next.