A configurable powerline-style status bar for Claude Code and Antigravity CLI, showing information such as the current folder, Git state, model, and context.

Use it to configure status-line segments, display branch and file-change indicators, and show AI-session details in either supported command-line tool.

It puts useful session and repository information in the terminal without requiring separate commands to check it.

gsl-status — Skill for Claude Code and Codex by sfc-gh-eraigosa

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/sfc-gh-eraigosa/dotfiles

agentmods

npx agentmods add skills/sfc-gh-eraigosa/dotfiles/skill

Made for: Claude Code, Codex.

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/skills/sfc-gh-eraigosa/dotfiles/skill/github.svg)](https://agentmods.dev/skills/sfc-gh-eraigosa/dotfiles/skill)

Your own site

<a href="https://agentmods.dev/skills/sfc-gh-eraigosa/dotfiles/skill"><img src="https://agentmods.dev/badge/skills/sfc-gh-eraigosa/dotfiles/skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sfc-gh-eraigosa/dotfiles/skill"><img src="https://agentmods.dev/badge/skills/sfc-gh-eraigosa/dotfiles/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,890 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 6 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Agent Snooping · line 13
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
high Agent Snooping · line 171
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
high Agent Snooping · line 180
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
high Agent Snooping · line 187
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
high Agent Snooping · line 43
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
high Agent Snooping · line 155
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl

How audits are shown

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	$0.00031	$0.03890
Opus 5.5	$0.00012	$0.01556
Sonnet 5.5	$0.00006	$0.00778
Haiku 4.5	$0.00003	$0.00389

Measured yesterday against content hash 165358d07cf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

gsl-status 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 yesterday.

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.

- **Antigravity CLI** (`agy`): pipes its payload to `~/.gemini/config/statusline-command.sh`

sdk/gsl/skill/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gsl — Go Status Line

gsl is a Go-based powerline-style status line. Both host CLIs drive it the same way: they pipe a JSON payload on stdin after every assistant turn and print whatever the shim writes to stdout.

Claude Code: pipes its payload to ~/.claude/statusline-command.sh; the shim execs gsl render, so stdin flows straight through to the binary.
Antigravity CLI (agy): pipes its payload to ~/.gemini/config/statusline-command.sh — the same shim, deployed to agy's config root — which also execs gsl render.

Note (changed in #157). agy is a first-class payload host. Older docs said to point agy's /statusline at gsl status and claimed "the ai segment self-omits under Antigravity because no payload is supplied". Both statements are false now. agy sends a full JSON payload (model, context window, quota, terminal width), and the ai segment renders under agy exactly as it does under Claude Code.

Segments

Segment	What it shows
`host`	Hardware-kind glyph (🍎 macOS, 🪟 WSL, 🍓 Pi, 🤖 Jetson, 🧠 DGX, 📦 container, 💻 other) + short hostname (floor 11 columns, grows to the full name when the line has room); far-left by default. Options: `min_len`, `max_len`, `icon`, `kind`
`dirgit`	Current directory name (basename, `~` for `$HOME`) + branch + staged/unstaged/untracked/stash/ahead/behind badges
`repo`	Root-or-worktree indicator glyph + optional feature/worker/branch name + optional PR badge (tinted by state) + optional worktree count badge; self-omits outside a git repo. Links: glyph → repo home, label → branch on GitHub, badge → the PR
`model` / `context` / `mcp` / `limits`	The AI segments (one `ai` segment until #426; `ai` still names all four): model name · context-window usage · MCP health (`6✓ 5✗ 1!` connected / failed / needs auth, shrinking to `6/12` → `6`; read from a cache, never probed during a render) · 5h/7d rate limits. Each toggles, moves and drops on its own; side by side they draw as one block. Render under both Claude Code and agy; self-omit only when there is no payload on stdin (e.g. bare `gsl status`)
`time`	Date + time formatted by config Go layouts + timezone abbreviation; always renders

Read the full file on GitHub · 230 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.

yesterday Changed · +4 lines 165358d07cf9
6d ago Changed · +5 lines ec7872888936
7d ago Changed · +1 lines a970c990be0f
18d ago Changed · +1 lines c3dc697ed5f3
1mo ago Changed · +22 lines 3e83015b7d11
1mo ago First seen · 197 lines · 31 tokens per session scan B bb1928a1eb95

Subscribe to this mod's changes

gsl-status is a skill published in the GitHub repository sfc-gh-eraigosa/dotfiles (50 stars, last pushed yesterday), licensed Apache-2.0. It adds 31 tokens to every session and 3,890 once invoked, about $0.0001 per session on Opus 5.5. 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.

Git and workflow Languages bash dotfiles shell works-with-codespaces zsh

macos-patterns

Essential native macOS development patterns that web developers don't know about. Use this skill whenever the user is building a macOS app and needs guidance on native patterns, or when they ask about menu bar apps, floating panels, window levels, keyboard shortcuts, file pickers, clipboard, drag and drop, screen…

freekmurze/dotfiles · 159 tokens

spatie-guidelines

Spatie's PHP, Laravel, JavaScript and Vue coding guidelines and conventions. Use when writing or reviewing PHP, Laravel, JavaScript, or Vue code for Spatie projects or packages. Covers code style, type declarations, docblocks, control flow, naming, routing, controllers, Blade, validation, comments, testing (Pest)…

freekmurze/dotfiles · 113 tokens

coding-best-practices

Reviews macOS Swift 6+ code for modern idioms, SOLID principles, SwiftData patterns, and concurrency best practices. Use when reviewing macOS code quality or asking about best practices.

freekmurze/dotfiles · 45 tokens

macos-release

Release a native macOS app to GitHub with DMG packaging and Sparkle appcast updates. Use this skill whenever the user wants to publish a new version, create a release, ship an update, push a release to GitHub, or update the appcast. Also trigger when the user mentions DMG creation, Sparkle signing, notarization…

freekmurze/dotfiles · 132 tokens

spatie-package-skeleton

Guide for creating PHP and Laravel packages using Spatie's package-skeleton-laravel and package-skeleton-php templates. Use when the user wants to create a new PHP or Laravel package, scaffold a package. Also use when building customizable packages — covers proven patterns for extensibility (events, configurable…

freekmurze/dotfiles · 78 tokens

speeding-up-laravel-tests

Use when Laravel/Pest test suites are slow, CI duration is growing, individual tests take seconds, or the user asks to speed up, optimize, or profile tests. Covers factories, fakes, config caching, XDebug/pcov, BCRYPTROUNDS, LazilyRefreshDatabase, and stray HTTP requests.

freekmurze/dotfiles · 72 tokens

gsl-status