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-metrics)<a href="https://agentmods.dev/commands/kubalajiri/claude-squirrel/squirrel-metrics"><img src="https://agentmods.dev/badge/commands/kubalajiri/claude-squirrel/squirrel-metrics/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-metrics"><img src="https://agentmods.dev/badge/commands/kubalajiri/claude-squirrel/squirrel-metrics.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 | $0.00248 |
| Opus 5 | $0.00012 | $0.00124 |
| Sonnet 5 | $0.00005 | $0.00050 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
squirrel-metrics scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run this exact command with the Bash tool and show the user its output verbatim:
sh "${CLAUDE_PLUGIN_ROOT}/scripts/squirrel.sh" --show-metrics
Read this before writing any task or bar rule. It prints the vocabulary of the version that is actually installed, which is the only one that can accept or refuse a condition — do not write a condition from memory of a metric name.
It lists every metric with its live value right now, a one-line meaning, the action verbs, and every field a task takes.
A ? means this invocation cannot know the value: either nothing has reported it yet, or the
metric is only knowable during a live render (ctx.pct, cost.usd and friends read the JSON
Claude Code pipes into the bar, which a command-line run does not have). A ? is not a broken
metric — but a condition over an unknown metric never fires, != included.
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.
- 9d ago First seen · 23 lines · 24 tokens per session scan A b54f0182c5ef
squirrel-metrics is a command published in the GitHub repository kubalajiri/claude-squirrel (2 stars, last pushed 15d ago), licensed MIT. It adds 24 tokens to every session and 248 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
hush
Silence all current and queued speech.
off
Disable narrator voice output.
buddy
Manage BuddyBar pet status, statusline, mode, evolution, prestige, and self-check.
i-have-adhd
Shape output for a reader with ADHD for the rest of this session.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.