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/tslateman/duet/install-statuslinegit clone --depth 1 https://github.com/tslateman/duetWrote 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/tslateman/duet/install-statusline)<a href="https://agentmods.dev/commands/tslateman/duet/install-statusline"><img src="https://agentmods.dev/badge/commands/tslateman/duet/install-statusline.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.00497 |
| Opus 5 | $0.00008 | $0.00249 |
| Sonnet 5 | $0.00003 | $0.00099 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade B, and why
install-statusline 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 3d 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.
- Current user statusline script: !`cat ~/.claude/statusline-command.sh 2>/dev/null || echo "(none)"` What it actually says
Install Statusline
Context
- Duet statusline script: !
cat statusline/statusline-command.sh - Current user statusline config: !
jq -r '.statusLine // empty' ~/.claude/settings.json 2>/dev/null || echo "(none)" - Current user statusline script: !
cat ~/.claude/statusline-command.sh 2>/dev/null || echo "(none)"
Your Task
Install the duet statusline script to ~/.claude/ and configure it in ~/.claude/settings.json.
-
Check current state:
- Does
~/.claude/settings.jsonalready have astatusLinefield? - Does
~/.claude/statusline-command.shalready exist? - Categorize: no existing statusline, identical, or different
- Does
-
If identical: Report "Statusline already up to date" and stop.
-
If different or new:
- If a statusline script already exists, show the diff between duet's version and the existing one
- Ask the user whether to install (replace) or skip
- Make clear this will overwrite their current statusline
-
Install:
- Copy
statusline/statusline-command.shto~/.claude/statusline-command.sh - Make it executable:
chmod +x ~/.claude/statusline-command.sh - If
~/.claude/settings.jsonlacks astatusLinefield, add it:"statusLine": { "type": "command", "command": "bash ~/.claude/statusline-command.sh" } - Use
jqto merge the statusLine field without disturbing other settings
- Copy
-
Verify:
- Confirm the script exists and is executable
- Confirm
settings.jsonhas thestatusLinefield - Report success — note that the statusline will appear on next Claude Code session start
Note
To disable the statusline, delete the statusLine key from settings.json entirely. Setting it to null causes a settings validation error.
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.
- 3d ago First seen · 50 lines · 15 tokens per session scan B 3d9530893539
install-statusline is a command published in the GitHub repository tslateman/duet (1 stars, last pushed 7d ago), licensed MIT. It adds 15 tokens to every session and 497 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.
Other commands, from other repositories
waterfall:quit
Cleanly stops the active workflow (shutdown teammates, marker cleanup, state preservation).
resume
Resumes an interrupted workflow at the current step.
import-codex
Import Codex session(s) into Claude Code, then resume into them.
status
Show the current Atelier mission board — progress, grouped tasks, the ready set, and a dependency graph.
gbu-retro
Post-session retrospective — harvest this session's lessons into durable doctrine.
gbu
Run the tiered multi-agent orchestration loop on a large task.