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/jaspersui/claude-code-iterm2-tab-status/configgit clone --depth 1 https://github.com/JasperSui/claude-code-iterm2-tab-statusWrote 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/jaspersui/claude-code-iterm2-tab-status/config)<a href="https://agentmods.dev/commands/jaspersui/claude-code-iterm2-tab-status/config"><img src="https://agentmods.dev/badge/commands/jaspersui/claude-code-iterm2-tab-status/config.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 | $0.00024 | $0.00546 |
| Opus 5 | $0.00012 | $0.00273 |
| Sonnet 5 | $0.00005 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
config 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 4d 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.
What it actually says
Read the current config file at ~/.config/claude-tab-status/config.json (create the directory if it doesn't exist). Merge with these defaults for any missing keys:
| # | Setting | Key | Default |
|---|---|---|---|
| 1 | Running prefix | prefix_running |
⚡ |
| 2 | Idle prefix | prefix_idle |
💤 |
| 3 | Attention prefix | prefix_attention |
🔴 |
| 4 | Flash color R (0-255) | color_r |
255 |
| 5 | Flash color G (0-255) | color_g |
140 |
| 6 | Flash color B (0-255) | color_b |
0 |
| 7 | Flash interval (seconds) | interval |
0.6 |
| 8 | Flash enabled | flash_enabled |
true |
| 9 | Badge enabled | badge_enabled |
true |
| 10 | Badge text | badge |
⚠️ Needs input |
| 11 | macOS notifications | notify |
false |
| 12 | Sound file path | sound |
(empty) |
| 13 | Display target | display_target |
title |
| 14 | Subtitle activity source | subtitle_activity_source |
off |
| 15 | Signal max age (seconds) | signal_max_age |
1800 |
Display all settings with their current effective values in a numbered table. Then ask the user which setting(s) they want to change. After they respond, update only the specified values and write the full config to ~/.config/claude-tab-status/config.json. The adapter will hot-reload the changes within ~1 second.
Validation rules:
color_r,color_g,color_b: integers 0-255interval: positive floatflash_enabled,badge_enabled,notify: booleandisplay_target: one oftitle,subtitle, orbothsubtitle_activity_source: one ofofforprompt;promptappends a compact sanitized snippet to the subtitle and is opt-in because prompt text may be sensitivesound: valid file path or empty stringsignal_max_age: integer seconds; expire signals not refreshed within this window (guards against tabs stuck on a stale status);0or negative disables age-based expiry
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.
- 4d ago First seen · 35 lines · 24 tokens per session scan A 9feaf0d5bca7
config is a command published in the GitHub repository JasperSui/claude-code-iterm2-tab-status (38 stars, last pushed 14d ago), licensed MIT. It adds 24 tokens to every session and 546 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
stats
Show token-saver compression statistics and savings.
release
Cut a signed, notarized Switchboard release (GitHub + Homebrew tap).
repeat
Replay the most recent Audio Recap audibly. Hits the per-session cache when available; otherwise generates on demand from the latest assistant turn.
off
Disable Audio Recap for this Claude Code session.
status
Print Audio Recap's current on/off state for this Claude Code session (no change).
on
Enable Audio Recap for this Claude Code session.