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.
npx agentmods add commands/briansmith80/claude-code-status-bar/setupgit clone --depth 1 https://github.com/briansmith80/claude-code-status-barWhat 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 | $0.00012 | $0.01429 |
| Opus 5 | $0.00006 | $0.00714 |
| Sonnet 5 | $0.00002 | $0.00286 |
| Haiku 4.5 | $0.00001 | $0.00143 |
Grade A, and why
setup 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 2d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-code-status-bar Setup
You are setting up the claude-code-status-bar plugin. Follow these steps exactly.
Step 1: Detect Environment
Run these commands to detect the platform and locate the plugin:
echo "OS: $(uname -s)" && echo "Shell: $SHELL" && echo "Home: $HOME"
Find the plugin installation directory:
plugin_dir=""
for d in "${CLAUDE_CONFIG_DIR:-$HOME/.claude}"/plugins/cache/claude-code-status-bar/claude-code-status-bar/*/; do
[ -d "$d" ] && plugin_dir="$d"
done
echo "Plugin dir: ${plugin_dir:-NOT FOUND}"
Step 2: Install Files
Copy the statusline script and helper to ~/.claude/:
target_dir="${CLAUDE_CONFIG_DIR:-$HOME/.claude}"
cp "${plugin_dir}statusline-command.sh" "${target_dir}/statusline-command.sh"
chmod +x "${target_dir}/statusline-command.sh"
# Copy Node.js helpers: live activity line + subagent panel rows
# (optional but recommended)
if [ -f "${plugin_dir}statusline-helper.js" ]; then
cp "${plugin_dir}statusline-helper.js" "${target_dir}/statusline-helper.js"
fi
if [ -f "${plugin_dir}statusline-subagent.js" ]; then
cp "${plugin_dir}statusline-subagent.js" "${target_dir}/statusline-subagent.js"
fi
# Copy version file
if [ -f "${plugin_dir}VERSION" ]; then
cp "${plugin_dir}VERSION" "${target_dir}/.statusline-version"
fi
# Commented config template: always refresh the reference, and create the live
# statusline.conf from it on first install only — never overwrite an existing one.
if [ -f "${plugin_dir}statusline.conf.example" ]; then
cp "${plugin_dir}statusline.conf.example" "${target_dir}/statusline.conf.example"
[ -f "${target_dir}/statusline.conf" ] || cp "${plugin_dir}statusline.conf.example" "${target_dir}/statusline.conf"
fi
echo "Files installed to ${target_dir}"
Step 3: Configure Settings
Read the current settings.json and merge in the statusLine configuration:
target_dir="${CLAUDE_CONFIG_DIR:-$HOME/.claude}"
settings_file="${target_dir}/settings.json"
command_value="bash ${target_dir}/statusline-command.sh"
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.
- 2d ago First seen · 128 lines · 12 tokens per session scan A 51eb97f43189
setup is a command published in the GitHub repository briansmith80/claude-code-status-bar (17 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 1,429 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 2026-08-30.
Other commands, from other repositories
r-review
You are the review command. You dispatch the reviewer subagent in.
r-test
You are the test command. You dispatch the UAT subagent to run.
r-verify
You are the verify command. You dispatch the QA subagent to run.
setup
Install the claude-pace statusline bundled with this plugin.
research
Enter RESEARCH mode for information gathering.
criar-skill
Use when creating new skills, automations, or specialized knowledge packages. Keywords: criar skill, nova skill, automatizar, conhecimento, TDD skill.