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 MadAppGang/magus/plugin install setupWrote 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/madappgang/magus/statusline-install)<a href="https://agentmods.dev/commands/madappgang/magus/statusline-install"><img src="https://agentmods.dev/badge/commands/madappgang/magus/statusline-install/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/madappgang/magus/statusline-install"><img src="https://agentmods.dev/badge/commands/madappgang/magus/statusline-install.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 | $0.00025 | $0.01511 |
| Opus 5.5 | $0.00010 | $0.00604 |
| Sonnet 5.5 | $0.00005 | $0.00302 |
| Haiku 4.5 | $0.00003 | $0.00151 |
Grade B, and why
statusline-install 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 22d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
3. Read `~/.claude/settings.json` How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
**Project scope:**
1. Write the script to `.claude/statusline-command.sh` in the current project root
2. Make it executable: `chmod +x .claude/statusline-command.sh`
3. Read the project's `.claude/settings.json` (create if needed)
4. Set the `statusLine` field to:
```json
{
"type": "command",
"command": "bash .claude/statusline-command.sh"
}
```
5. Write back the updated settings (preserve all other fields)
**Global scope:**
1. Write the script to `~/.claude/statusline-command.sh`
2. Make it executable: `chmod +x ~/.claude/statusline-command.sh`
3. Read `~/.claude/settings.json`
4. Set the `statusLine` field to:
```json
{
"type": "command",
"command": "bash ~/.claude/statusline-command.sh"
}
```
5. Write back the updated settings (preserve all other fields)
**4a. Probe for a patched font (fast, no dependencies).**
Do NOT use `fc-list` — fontconfig is usually absent on macOS. Scan the font
directories by filename instead:
```bash
find ~/Library/Fonts /Library/Fonts /System/Library/Fonts \
-maxdepth 2 \( -type f -o -type l \) 2>/dev/null \
| grep -Ei 'nerd|NF-|powerline' | head -5
```
**4b. No matches → do not ask.** Write `icons.nerd_font: false` (see 4d) and
move on. Mention it in the report as one line, nothing more.
**4c. Matches found → ask, showing the real glyph.** A font inventory is NOT
enough to decide: Nerd Font coverage is **partial and varies by font**. On a
machine with 0xProto Nerd Font installed, `U+F035B` (nf-md-memory) renders
correctly while `U+F2DB` (nf-fa-microchip) and `U+F4BC` (nf-oct-cpu) come out
as blank space. Only the user can confirm the specific glyph resolves.
Print the sample line first — it must contain the actual glyph the plugin
will use, in context:
```
Found a Nerd Font: <first matching filename>
With icons: 1.1G
Without icons: RAM 1.1G
```
Then use AskUserQuestion:
- question: "In the line above, do you see a RAM-stick icon before `1.1G`?"
- options:
1. "Yes, I see an icon" — enables Nerd Font glyphs (`icons.nerd_font: true`)
2. "No — a box, or blank space" — keeps text labels (`icons.nerd_font: false`)
"Blank space" is an explicit option on purpose: a missing glyph often renders
as nothing rather than as tofu, and a user skimming for a box will answer yes
to an empty gap.
**4d. Write the answer, merging — never clobbering.**
The config file is `~/.claude/statusline-config.json` for **both** scopes: the
script always reads it from `$HOME`, even when installed project-scoped.
1. Read `~/.claude/statusline-config.json` (may not exist — then start from `{}`)
2. Set only `icons.nerd_font` to the boolean answer, leaving every other key
untouched (users commonly have `sections`, `theme`, `context_bar_width`)
3. Write the merged object back
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.
- 22d ago Changed 787a55b6150c
- 1mo ago Changed 04a391f97061
- 1mo ago First seen · 152 lines · 25 tokens per session scan B 580682340714
statusline-install is a command published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 1,511 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-04.
Other commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
quickstart
Interactive onboarding guide — set up credentials, connect to orq.ai, and learn every command and skill.
r
Resume the last handoff and carry on with the outstanding work.
focus
You are an ADHD focus assistant. Help the user commit to ONE task and block mental distractions.
stuck
You are an ADHD-friendly unblocking assistant. Help users get unstuck when they don't know what to do.