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 skills add stormzhang/token-tracker --skill tt_sidebar_kimigit clone --depth 1 https://github.com/stormzhang/token-trackerWrote 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/skills/stormzhang/token-tracker/tt_sidebar_kimi)<a href="https://agentmods.dev/skills/stormzhang/token-tracker/tt_sidebar_kimi"><img src="https://agentmods.dev/badge/skills/stormzhang/token-tracker/tt_sidebar_kimi.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.00240 |
| Opus 5 | $0.00026 | $0.00120 |
| Sonnet 5 | $0.00010 | $0.00048 |
| Haiku 4.5 | $0.00005 | $0.00024 |
Grade A, and why
tt-sidebar 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 8d 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
TT Sidebar
Run the installed launcher exactly once:
__TT_SIDEBAR_COMMAND__
The launcher splits tmux, iTerm2, or Ghostty (macOS, ≥ 1.3.0) to open the sidebar pane, so it needs permission to control the terminal. If the runtime asks for approval, approve this exact command only; never approve Python generally.
Return the launcher's output directly. Do not run regular tt sidebar, inject a command into a transient shell, or open another sidebar in the current pane. If the launcher fails, report only its concise stage error.
The launcher must keep the source pane focused and open a right-side pane at one-third width. The split view is current-session-only and is intentionally independent from the regular all-session tt sidebar layout.
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.
- 8d ago First seen · 23 lines · 51 tokens per session scan A f3075b712eac
tt-sidebar is a skill published in the GitHub repository stormzhang/token-tracker (509 stars, last pushed 13d ago), licensed MIT. It adds 51 tokens to every session and 240 once invoked, about $0.0003 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 skills, from other repositories
gws-calendar
Google Calendar: Manage calendars and events.
gws-gmail-reply
Gmail: Reply to a message (handles threading automatically).
gws-gmail-send
Skill "gws-gmail-send" from googleworkspace/cli, covering gmail +send, usage, flags, examples and tips.
gws-gmail-watch
Gmail: Watch for new emails and stream them as NDJSON.
gws-gmail
Gmail: Send, read, and manage email.
gws-calendar-insert
Google Calendar: Create a new event.