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 atretyak1985/swarmery/plugin install accounts-packWrote 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/atretyak1985/swarmery/account)<a href="https://agentmods.dev/commands/atretyak1985/swarmery/account"><img src="https://agentmods.dev/badge/commands/atretyak1985/swarmery/account/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/atretyak1985/swarmery/account"><img src="https://agentmods.dev/badge/commands/atretyak1985/swarmery/account.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 | $0.00056 | $0.01622 |
| Opus 5 | $0.00028 | $0.00811 |
| Sonnet 5 | $0.00011 | $0.00324 |
| Haiku 4.5 | $0.00006 | $0.00162 |
Grade A, and why
account 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.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/account — which account does this project run under?
Usage
/account list the accounts and mark the one this project uses
/account use <key> bind this project to an account
/account clear drop the binding (back to the default account)
/account setup-shell [--uninstall] install/remove the `claude` shell function in your profile
What it does — and does not do
This is a thin proxy over the swarmery account CLI. It parses
$ARGUMENTS, picks the matching command below, and reports its output. It owns
no logic of its own: what an account is, where its config dir lives, and what
the environment delta is are all answered by the CLI, so this command and the
dashboard can never give different answers.
If a rule about accounts ever appears in this file, it leaked out of the CLI and belongs back there.
Requires the swarmery CLI on PATH. It does not require the daemon:
which, use, clear, env and exec read and write the binding file
directly. If swarmery is missing, say so and stop — do not guess an account.
Commands
/account (no arguments)
swarmery account list
swarmery account which --path "${CLAUDE_PROJECT_DIR:-$PWD}"
Report both: the table of installed accounts (key, config dir, default?,
connected?, plan) and the account this project effectively runs under. source: binding means someone chose it; source: default means nobody did.
connected: unknown is not no — it means credential resolution is switched
off (SWARMERY_USAGE_OAUTH=0), so the question was never asked.
/account use <key>
swarmery account use "<key>" --path "${CLAUDE_PROJECT_DIR:-$PWD}"
Writes the binding to .claude/settings.local.json (machine-local, gitignored —
two people on one repo legitimately use different accounts). The CLI refuses a
key that is not installed on this machine; report that refusal as-is rather than
falling back to another account.
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 · 156 lines · 56 tokens per session scan A 4e2be8dfc7a3
account is a command published in the GitHub repository atretyak1985/swarmery (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 56 tokens to every session and 1,622 once invoked, about $0.0003 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
save-to-md
Save session documentation with Neo4j memory integration.
gws-docs
Read, create, and append content to Google Docs documents.
gws-chat
Send messages and manage Google Chat spaces.
gws-standup
Generate a standup report combining today's calendar and tasks.
send-email
Send an email via Google Workspace CLI.
meeting-prep
Prepare for your next meeting with agenda and attendees.