A command for installing or updating exline's background status service, checking its requirements, building it, starting it, and registering it.

Use it after installing or updating exline to verify dependencies and prepare the daemon.

It provides the setup sequence needed for the status service to work with the installed plugin version.

setup — Command by manymee

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/manymee/claude-plugins/setup

Clone the repo

git clone --depth 1 https://github.com/manymee/claude-plugins

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 980 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00024	$0.00980
Opus 5	$0.00012	$0.00490
Sonnet 5	$0.00005	$0.00196
Haiku 4.5	$0.00002	$0.00098

Measured yesterday against content hash dafdf1cde885, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

setup scanned grade B with 1 finding 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 yesterday.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`~/.claude/settings.json` (ask first, and show the change):

plugins/exline/commands/setup.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Set up (or update) the exline statusline daemon on this machine. This command is idempotent: run it after installing the plugin, and again after every plugin update (the statusline shows a "run /exline:setup" warning line when the installed plugin version differs from the running daemon).

Work through the steps below in order. Stop and tell the user what's missing if a prerequisite fails; don't half-install.

1. Resolve paths

Plugin root: ${CLAUDE_PLUGIN_ROOT}. If that literal string appears unexpanded above, resolve it instead from ~/.claude/plugins/installed_plugins.json: the entry whose key starts with exline@ has an installPath.
Data dir (survives plugin updates; the versioned plugin root does not): ~/.claude/plugins/data/exline-<marketplace> where <marketplace> is the part after @ in that registry key. Create it if missing.

2. Check dependencies

jq and nc must be on PATH (the client uses both).
elixir and mix must be on PATH. Elixir ~> 1.19 on OTP 28 is what's tested (mise.toml records the exact versions); mix.exs rejects older Elixir at build time.
Only check — never install anything on the user's behalf. If something is missing, report exactly what's needed (e.g. brew install jq; Elixir via brew/mise/asdf — their choice) and stop.

3. Build the release

From the plugin root:

mix deps.get --only prod
MIX_ENV=prod mix release --overwrite --path "<DATA>/rel"

Then install the client at a stable path:

install -m 755 "<PLUGIN_ROOT>/client" "<DATA>/client"

4. Start the daemon

If ~/Library/LaunchAgents/com.manymee.exline.plist already exists, the user has already chosen launchd: refresh and restart it (steps below) without asking. Otherwise this is first-time setup — ask before touching launchd: launchd (recommended — starts at login, restarts on crash) or a one-off manual start, and respect a decline.

launchd (macOS): render <PLUGIN_ROOT>/launchd/com.manymee.exline.plist.template — replace __BIN__ with <DATA>/rel/bin/exline, __WORKDIR__ with <DATA>, __LOG__ with $HOME/Library/Logs/exline.launchd.log (absolute paths, no ~) — and write it to ~/Library/LaunchAgents/com.manymee.exline.plist. Then:

Read the full file on GitHub · 93 lines

Changes

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.

yesterday First seen · 93 lines · 24 tokens per session scan B dafdf1cde885

Subscribe to this mod's changes

setup is a command published in the GitHub repository manymee/claude-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 980 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Planning

setup

Getting it into your agent

What it costs to keep this loaded

Grade B, and why

Reads agent configuration directoriesmediumAgent snooping

How it starts

1. Resolve paths

2. Check dependencies

3. Build the release

4. Start the daemon

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement