squirrel-bg

squirrel-bg is a command for Claude Code from kubalajiri/claude-squirrel. It costs 24 tokens per session (334 once invoked), scanned A, original, MIT.

A command for configuring background colours on a full-width session status bar. It controls the warning phase, the later alarm phase, or whether the background is shown at all.

In plain words
What is it for?
Use it to set or disable warning and alarm colours, control the alarm-phase background separately, and configure additional idle phases with their text and boldness settings.
Why use it?
It gives waiting sessions a visible warning that becomes more urgent over time, without requiring you to inspect a small status indicator.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the squirrel plugin — 1 skill, 37 commands, 6 hooks shipped together

Good fit Use it to set or disable warning and alarm colours, control the alarm-phase background separately, and configure additional idle phases with their text and boldness settings.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add kubalajiri/claude-squirrel
Claude Code
/plugin install squirrel

Made for: Claude Code.

Or install squirrel, the plugin that ships this one along with the rest of its 1 skill, 37 commands, 6 hooks.

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.

agentmods badge for squirrel-bg

README.md
[![agentmods](https://agentmods.dev/badge/commands/kubalajiri/claude-squirrel/squirrel-bg/github.svg)](https://agentmods.dev/commands/kubalajiri/claude-squirrel/squirrel-bg)
Your own site
<a href="https://agentmods.dev/commands/kubalajiri/claude-squirrel/squirrel-bg"><img src="https://agentmods.dev/badge/commands/kubalajiri/claude-squirrel/squirrel-bg/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.

agentmods 80×15 button for squirrel-bg

Your own site · 80×15
<a href="https://agentmods.dev/commands/kubalajiri/claude-squirrel/squirrel-bg"><img src="https://agentmods.dev/badge/commands/kubalajiri/claude-squirrel/squirrel-bg.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 334 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.00334
Opus 5 $0.00012 $0.00167
Sonnet 5 $0.00005 $0.00067
Haiku 4.5 $0.00002 $0.00033

Measured 8d ago against content hash b9be41997fcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

squirrel-bg 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 8d 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.

plugin/commands/squirrel-bg.md · 23 lines

What it actually says

Run this exact command with the Bash tool and show the user its output verbatim:

sh "${CLAUDE_PLUGIN_ROOT}/scripts/squirrel.sh" --set-bg "$ARGUMENTS"

/squirrel-bg <colour|off> sets the warn-phase banner colour shown once a session has been waiting past idleBackgroundAfterSeconds (a clearly visible yellow, #c9a227, by default — bold white text) — a hazard-banner-style warning, not a subtle tint. /squirrel-bg urgent <colour|off> sets the alarm-phase bar colour that takes over once the wait also passes alarmAfterSeconds — the same trigger as the loud chip — painting the whole bar in that colour (strong red, #b3261e, by default) with bold white text. These two phases are really the first two entries of the full idle-phase ladder (see /squirrel-phases for any phase beyond these two, or to change text/bold per phase — e.g. --set-phase 30 text=black bold=off). urgent off paints no background at the alarm phase (the loud chip and its text colour still apply) rather than falling back to the warn-phase colour; /squirrel-bg off disables all painting outright.

Do not do anything else.

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.

  1. 8d ago First seen · 23 lines · 0 tokens per session scan A b9be41997fcc

Subscribe to this mod's changes

squirrel-bg is a command published in the GitHub repository kubalajiri/claude-squirrel (2 stars, last pushed 14d ago), licensed MIT. It adds 24 tokens to every session and 334 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 2026-08-31.