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-custom)<a href="https://agentmods.dev/commands/kubalajiri/claude-squirrel/squirrel-custom"><img src="https://agentmods.dev/badge/commands/kubalajiri/claude-squirrel/squirrel-custom.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 5.1 | $0.00019 | $0.00681 |
| Opus 5 | $0.00010 | $0.00341 |
| Sonnet 5 | $0.00004 | $0.00136 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
squirrel-custom scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run this exact command with the Bash tool and show the user its output verbatim:
sh "${CLAUDE_PLUGIN_ROOT}/scripts/squirrel.sh" --custom "$ARGUMENTS"
With no arguments this lists every custom segment, what it does, and whether it is showing right now.
| Field | Values | Effect |
|---|---|---|
text |
any text (takes the rest of the line) | static text to show |
command |
a shell command (rest of the line) | its first line of output becomes the text |
every |
30m 2h 90s or seconds |
with ack: how long after dismissing before it returns. Without ack: how often a command is re-run |
at |
HH:MM (24-hour) |
show from that time of day |
ack |
on / off |
can be dismissed with /squirrel-done |
shared |
on / off |
keep the dismissal in the cross-profile store, so it clears in every session and every alias at once |
when |
a condition (rest of the line) | only show while it holds — same grammar as /squirrel-rules |
line |
1, 2, … |
which line it joins |
link |
https://… |
make it clickable where the terminal supports OSC-8 |
text=, command= and when= swallow the rest of the line, so put one of them last;
use a second set for another. add needs text= or command= — never both.
Reminders are just this. There is no separate reminder feature:
/squirrel-custom add water every=30m ack=on shared=on text=💧 drink water
/squirrel-custom add break every=2h ack=on shared=on text=🧘 take a break
Dismiss with /squirrel-done <id> (or all), or push one out with
/squirrel-snooze <id> <minutes>. A reminder that has never been dismissed shows straight
away, which is how the user sees that it worked.
command= does nothing until commands are switched on with /squirrel-custom-commands on
— they are off by default. Tell the user that plainly if they add one; --show-custom
marks such segments BLOCKED with the command to run. A command never runs while the bar is
drawing: its output is cached and refreshed in the background, so the first render after
adding one shows nothing and the next shows the value.
Every edit validates before writing; a refused edit changes nothing. Never write the
customSegments 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.
- 7d ago First seen · 47 lines · 19 tokens per session scan A 227510d6b6c4
squirrel-custom is a command published in the GitHub repository kubalajiri/claude-squirrel (2 stars, last pushed 13d ago), licensed MIT. It adds 19 tokens to every session and 681 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
todo
The quality-gated task list: tasks with real descriptions, testable acceptance criteria, and evidence — a task only closes when the controller agrees it is done.
ask
Ask a single expert agent a question - like a Slack ping to a colleague.
rows
Configure which rows cc-statusline shows (or turn it off entirely).
config
Configure iterm2-tab-status plugin settings (emoji prefixes, colors, display target, subtitle activity, badge, notifications).
statusline
Show the governor fleet in your Claude Code statusline. Explicit, opt-in, and chains — it never replaces an existing statusline.
pin
Break checkpoint — status display, session log, optional MEMORY.md update.