Claude Powerline is a vim-style statusline for Claude Code that displays information such as usage and Git status in the terminal. It is for Claude Code users who want a configurable session display, and the catalogue entries provide its plugin and command.
Borrowing it
Nothing to install: this file belongs to Owloops/claude-powerline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Owloops/claude-powerline/main/AGENTS.mdgit clone --depth 1 https://github.com/Owloops/claude-powerlineWrote 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/owloops/claude-powerline/agents-md)<a href="https://agentmods.dev/instructions/owloops/claude-powerline/agents-md"><img src="https://agentmods.dev/badge/instructions/owloops/claude-powerline/agents-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.
<a href="https://agentmods.dev/instructions/owloops/claude-powerline/agents-md"><img src="https://agentmods.dev/badge/instructions/owloops/claude-powerline/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01304 | $0.01304 |
| Opus 5.5 | $0.00522 | $0.00522 |
| Sonnet 5.5 | $0.00261 | $0.00261 |
| Haiku 4.5 | $0.00130 | $0.00130 |
Grade A, and why
claude-powerline AGENTS.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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project overview
claude-powerline is a statusline for Claude Code, published on npm as @owloops/claude-powerline. Claude Code runs it on every render, passing hook data as JSON on stdin; it prints the line and exits, so render time is paid on every refresh. It has zero runtime dependencies.
Tech stack
- TypeScript (ESM), built with tsdown, tested with Jest through ts-jest.
- Node.js 18+ (
engines); the main bundle targetsnode18. scripts/bench.tsruns unbuilt, through Node's type stripping (Node 22.18+): erasable TypeScript only (no enums, no parameter properties).- semantic-release publishes from
main: commit types decide the version and generateCHANGELOG.md.
Project settings
TypeScript, tsconfig.json:
strict,noUncheckedIndexedAccess,noImplicitReturnsandnoImplicitOverrideare on: an indexed access is possiblyundefined.test/is excluded.
Repository structure
src/index.ts: CLI entry;src/powerline.tsassembles the line.src/segments/: one data provider per segment (context,session,today,block,git,metrics…) andrenderer.ts, the classic powerline renderer.src/tui/: the TUI renderer and its layouts; it renders the same segments in a box.src/utils/claude.ts: hook data types and transcript (JSONL) reading.src/config/: config loading anddefaults.ts.src/browser.ts: a second entry with no Node built-ins, exporting the renderers, themes and types for browser use.plugin/: the Claude Code plugin and its/powerlinesetup wizard.scripts/bench.ts: the comparative benchmark (see Performance).pricing.json: generated weekly by.github/workflows/pricing.yml; do not edit by hand.
Commands
npm run typecheck: type-checkssrc/andscripts/.npm run lint: ESLint with Prettier onsrc/.npm test: the Jest suite, and the only type check oftest/.npm run build: buildsdist/with tsdown;bin/claude-powerlinerunsdist/index.mjs.npm run bench: the comparative benchmark (see Performance).
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.
- today First seen · 77 lines · 1,304 tokens per session scan A f207d4e2e40b
claude-powerline AGENTS.md is an instructions file published in the GitHub repository Owloops/claude-powerline (1,175 stars, last pushed yesterday), licensed MIT. It adds 1,304 tokens to every session, about $0.0052 per session on Opus 5.5. 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 2026-11-07.
claude-powerline AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-powerline AGENTS.mdOwloops/claude-powerline | Instructions file | 1.2k | yesterday | MIT | A | 1,304 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |