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 commands/briansmith80/claude-code-status-bar/configuregit clone --depth 1 https://github.com/briansmith80/claude-code-status-barWrote 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/commands/briansmith80/claude-code-status-bar/configure)<a href="https://agentmods.dev/commands/briansmith80/claude-code-status-bar/configure"><img src="https://agentmods.dev/badge/commands/briansmith80/claude-code-status-bar/configure.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 | $0.00012 | $0.03125 |
| Opus 5 | $0.00006 | $0.01563 |
| Sonnet 5 | $0.00002 | $0.00625 |
| Haiku 4.5 | $0.00001 | $0.00313 |
Grade A, and why
configure scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-code-status-bar — Guided configuration wizard
You are a setup wizard for the user's status bar. Walk them through a short,
guided sequence of choices using the AskUserQuestion tool (one question
group at a time), then write only the non-default settings to
~/.claude/statusline.conf. Be friendly and fast. The whole point is that
Claude Code is the interactive layer — the user should never hand-edit a file
unless they want to.
Rules for every question:
- Make the FIRST option the user's CURRENT value (or the default), labelled "(keep current)". This lets them breeze through with one keypress.
- Use
multiSelect: truefor the toggle groups (Q3–Q5). - Skip any group the user says they don't care about. Don't force all six.
- After the questions, PREVIEW before you save, then write only the diff.
Step 1 — Read the current config and orient
conf_file="${CLAUDE_CONFIG_DIR:-$HOME/.claude}/statusline.conf"
if [ -f "$conf_file" ]; then echo "=== current statusline.conf ==="; cat "$conf_file"; else echo "No config yet — all defaults."; fi
Summarise the current state in one or two plain sentences (theme, layout, and anything already non-default). Then offer to preview the themes live — this is the closest thing to a visual picker and it shows each theme's gradient bars:
bash ~/.claude/statusline-command.sh --demo
Step 2 — Run the guided questions (AskUserQuestion)
Ask these as a sequence of AskUserQuestion calls. You can batch up to 4 related questions per call. For each option list, lead with the current/default value.
Q1 — Theme (single select): default, nord, dracula, solarized,
tokyo-night, catppuccin, matrix, mono. Tell them they can run
--demo <theme> to preview just one. (Offer 4 at a time if listing all eight;
or ask "which family — neon / muted / pastel / mono?" first, then narrow.)
Q2 — Layout (single select):
classic— every metric on line 1, live activity on line 2 (the default)three-line— model/usage/cost · dir + git state · activitystacked— dir/model/usage · git state/duration · activity
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 · 196 lines · 12 tokens per session scan A a4bfa95ea2ca
configure is a command published in the GitHub repository briansmith80/claude-code-status-bar (17 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 3,125 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
ssh-keys
Manage SSH keys across hosts — generate, sync, list status, or delete.
pi-code-review
Adversarial code review via Codex — break confidence in changes, not validate them.
pi-askall
Ask both Codex and Gemini the same question — get three perspectives with Claude synthesis.
setup
Install the claude-pace statusline bundled with this plugin.
pi-ask-gemini
Ask Gemini a question — get Google's perspective alongside Claude's.
voice-test
Test the complete AudioBash voice transcription pipeline including all providers, API key configuration, and agent mode prompts.