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.
/plugin marketplace add kubalajiri/claude-squirrel/plugin install squirrelWrote 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/kubalajiri/claude-squirrel/squirrel-style)<a href="https://agentmods.dev/commands/kubalajiri/claude-squirrel/squirrel-style"><img src="https://agentmods.dev/badge/commands/kubalajiri/claude-squirrel/squirrel-style/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/commands/kubalajiri/claude-squirrel/squirrel-style"><img src="https://agentmods.dev/badge/commands/kubalajiri/claude-squirrel/squirrel-style.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 | $0.00024 | $0.00706 |
| Opus 5 | $0.00012 | $0.00353 |
| Sonnet 5 | $0.00005 | $0.00141 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
squirrel-style scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run this exact command with the Bash tool and show the user its output verbatim:
sh "${CLAUDE_PLUGIN_ROOT}/scripts/squirrel.sh" --style "$ARGUMENTS"
With no arguments this lists every segment that carries a style and the fields available.
| Field | Values | Effect |
|---|---|---|
fg |
colour name, #rrggbb, or auto |
foreground colour |
bg |
colour name, #rrggbb, or auto |
background behind the segment |
bold |
on / off |
bold text |
opacity |
0.0–1.0, or auto |
fades the text toward the background |
sep |
dot bar space none, or auto |
the punctuation printed before this segment |
force |
on / off |
let fg/opacity override meaning-carrying colours too |
The rule to explain when asked: a warning always breaks through. fg and opacity
recolour anything decorative — the all-clear green, a clean branch's grey, the dimmed token
counts — but never a yellow or red one. A usage bar that turns red at 80%, the yellow
session-reset countdown and a dirty-branch marker keep their colours, so styling a segment can
never make it stop warning you. force=on opts out of that; only suggest it when the user
clearly wants total control.
opacity is a real alpha blend toward the idle phase banner's colour while one is painted.
When no banner is painted there is no knowable background, so it falls back to the terminal's
own dim attribute — and it does the same for named ANSI colours, whose actual RGB is the
terminal's choice rather than something we can blend against honestly.
While an idle phase banner or a bar rule is painting the whole line, its background is
applied last and covers a segment's own bg — the style is not broken, it is underneath.
Say so if a user reports their background vanishing during an idle alarm.
sep is what to reach for when a reordered layout punctuates oddly — a segment moved next to
a group it does not belong to keeps that group's separator until you override it.
set <segment> <field>=<value> ...overlays only the fields given, leaving the segment's other fields (and every other segment) untouched.autoclears one field.clear <segment>drops that segment's whole style;resetdrops all of them.
Every edit validates before writing: an unknown segment, an invalid colour, an out-of-range
opacity, or an unknown separator is refused and nothing is written. Never write the
segmentStyles config key by hand — always go through this command.
Do not do anything else.
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.
- 8d ago First seen · 49 lines · 24 tokens per session scan A cca0add170cc
squirrel-style 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 706 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.
Other commands, from other repositories
anti-slop-designer
Use when a UI looks machine-made rather than decided. Violet gradients, glassmorphism everywhere, identical cards in a grid, untouched shadcn or Material defaults, emoji bullets, or copy stuffed with seamless and unlock.
design-enforce
Use when code has drifted off the design system. Raw hex values and pixel numbers written where a token already exists, one-off components, library defaults left untouched. Finds every bypass and fixes it.
design-grill
Use when a design keeps getting reinvented every session. Interviews you until you share one understanding, then writes the vocabulary and the binding decisions into the repo so they survive the next context window.
audit
Run a full UI/UX design audit on the current project. Scores 12 dimensions and produces a markdown report with prioritized findings.
design-triage
Use when a dwic audit report is full of findings and there is no plan. Ranks them into an order someone can work through, then works through it.
accessibility-specialist
Use when a screen might fail WCAG. Unlabeled inputs, no keyboard path, contrast below AA, missing landmarks, broken heading order, screen reader gaps, or a request for an a11y review or EU Accessibility Act check.