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 Beezi-AI/beezi-claude-plugin/plugin install beeziWrote 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/beezi-ai/beezi-claude-plugin/settings)<a href="https://agentmods.dev/commands/beezi-ai/beezi-claude-plugin/settings"><img src="https://agentmods.dev/badge/commands/beezi-ai/beezi-claude-plugin/settings/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/beezi-ai/beezi-claude-plugin/settings"><img src="https://agentmods.dev/badge/commands/beezi-ai/beezi-claude-plugin/settings.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 | $0.00000 | $0.08647 |
| Opus 5.5 | $0.00000 | $0.03459 |
| Sonnet 5.5 | $0.00000 | $0.01729 |
| Haiku 4.5 | $0.00000 | $0.00865 |
Grade A, and why
settings 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 — 549 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Do NOT read, open, or inspect any files. Never echo any token.
Arguments: $ARGUMENTS
The user cannot see tool output: Claude Code collapses it after a few lines. A script's output
reaches the user only through your reply text or a question's preview, so output you are told
to show is copied VERBATIM into your reply, as its very first text: exactly as printed, never
summarized, paraphrased, reformatted or replaced by a sentence of your own ("I've noted…" is
wrong). Machine lines (key=value lines, and every line of an output you are told not to show)
are never shown.
Previews: whenever a single-select question below says "with previews", give EVERY option a
preview holding the named script output, copied exactly (a markdown table stays a table). The
preview is what the user reads while choosing, so never leave it out.
AskUserQuestion, everywhere below: at most 4 questions in one call and at most 4 options in one
question; multiSelect: true only with 2 or more options. Make one AskUserQuestion call per
message and wait for its answers before the next (two calls in one message show the user only
the last). A dismissed question runs nothing.
Read the settings: one command
Everything this command reads comes from ONE command, picked by the first word of the arguments. Run it once, first, and take everything below from its output: never run a read again, nor another script to read settings. The commands below only change settings or refresh the plan.
| First word of the arguments | Run EXACTLY |
|---|---|
show alone |
node ${CLAUDE_PLUGIN_ROOT}/scripts/settings.mjs all |
rules |
node ${CLAUDE_PLUGIN_ROOT}/scripts/settings.mjs rules |
new-folders |
node ${CLAUDE_PLUGIN_ROOT}/scripts/settings.mjs new-folders |
account |
node ${CLAUDE_PLUGIN_ROOT}/scripts/settings.mjs account |
telemetry or statusline, alone or + show |
node ${CLAUDE_PLUGIN_ROOT}/scripts/settings.mjs privacy |
telemetry <mode> or statusline on/off |
nothing: go to Crash reports & status line |
statusline badge on/off |
nothing: go to Crash reports & status line |
refresh |
nothing: go to Refresh my Claude plan |
undo |
nothing: run node ${CLAUDE_PLUGIN_ROOT}/scripts/workspace.mjs undo and write its first line verbatim; stop |
| nothing, or anything else | node ${CLAUDE_PLUGIN_ROOT}/scripts/settings.mjs |
Its output is blocks, each from a <name …> line to its </name> line:
<show>— always first. Write its lines (not the tag lines) verbatim as your reply's first text.<keys>— for you only:menu=<label>|<label>…— the sections that apply here;- one line per linked account:
account=<key> default=<yes|no> multi=<yes|no> workspaces=<n> status=<…> email=<email>(multi=yes: the account is in several workspaces;workspaces=<n>is its known workspace count,0when not known yet; no such line: nothing is linked); crash=<correlate|on|anonymous|off> statusline=<on|off> badge=<on|off>.
<labels>— with no arguments only: one line permenu=label, in the same order, the label with its current state (e.g.Rules: here → Acme,New folders: ask me,Account: 2 linked); these are the menu question's option labels.<rules account="<key>">— one per account whose workspaces are known (with no arguments, orrules); see Rules.<here-card account="<key>">— one per such account when this folder is known (with no arguments, orrules): where you are and where its analytics go now; a preview for Rules.<new-folders account="<key>">— one per account in several workspaces (with no arguments, ornew-folders); see New folders.<preview section="<label>">— one per menu section (with no arguments only).
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 Changed · +65 lines 93a24bc29adf
- 23d ago First seen · 484 lines · 0 tokens per session scan A bbdb119002a0
settings is a command published in the GitHub repository Beezi-AI/beezi-claude-plugin (63 stars, last pushed 9d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 8,647 tokens. 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 2026-10-15.
settings compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| settingsBeezi-AI/beezi-claude-plugin | Command | 63 | 9d ago | Apache-2.0 | A | 0 | Claude Code |
| huntsoheilfallah/jobxhunter | Command | 9 | 2mo ago | MIT | A | 20 | Claude Code |
| cc-probeline-configlabzink/cc-probeline | Command | 12 | 2mo ago | MIT | A | 21 | Claude Code |
| orchestrateegorfedorov/claude-context-optimizer | Command | 130 | 10d ago | MIT | A | 0 | Claude Code |
| todo.templateevan043/claude-cli-advanced-starter-pack | Command | 61 | 3mo ago | MIT | A | 0 | Claude Code |
| clean-checkTeamManagementPlugin/claude-plugin | Command | 6 | 23d ago | MIT | A | 27 | Claude Code |
| notessystemoperators/claude-plugins | Command | 6 | 3d ago | MIT | A | 6 | Claude Code |