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 skills/agenkin/telemetrydeck-analytics/setupnpx skills add agenkin/telemetrydeck-analytics --skill setupgit clone --depth 1 https://github.com/agenkin/telemetrydeck-analyticsWhat 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 | $0.00029 | $0.00393 |
| Opus 5 | $0.00015 | $0.00197 |
| Sonnet 5 | $0.00006 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00039 |
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.
What it actually says
Setup
tdq login requires a real TTY for interactive prompts. Claude Code's Bash tool is not a TTY, so attempt the login and handle the two cases:
Case 1 — credentials not yet stored (first run)
Running tdq login via Bash will fail with:
stdin is not a TTY — cannot prompt for email.
Run `tdq login` directly in your terminal.
Tell the user: open a terminal and run tdq login. Walk them through what to expect:
- TelemetryDeck email prompt
- Password prompt (hidden)
- Numbered app picker — type the number next to their app and press Enter
- A login summary is printed on success
Once they confirm it completed, run tdq doctor via Bash to verify the token is live.
Case 2 — credentials already stored, only app selection needed
If email + password are already in the keychain (e.g. re-setup after switching apps), the non-TTY error will be on the app picker step. The CLI prints the app list before exiting. Read the app names and UUIDs from the error output and ask the user which app to use. Then run:
tdq login --app-id <chosen-uuid>
--app-id skips the picker entirely and works non-interactively.
Case 3 — $ARGUMENTS contains a UUID
Skip the picker immediately:
tdq login --app-id $ARGUMENTS
After any successful login
Run tdq doctor and relay the output so the user sees the end-to-end health check pass.
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 · 49 lines · 29 tokens per session scan A 92ec65a109f3
setup is a skill published in the GitHub repository agenkin/telemetrydeck-analytics (2 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 393 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 2026-08-31.
Other skills, from other repositories
motion-canvas
Motion Canvas framework reference covering project setup, core concepts (generators, signals, refs, scene hierarchy, timing, utilities), and 2D components (shapes, paths, text, media, layout, camera, transitions, custom components). Use when building or editing Motion Canvas scenes.
motion-canvas-agent
Agent tooling for Motion Canvas — seek, screenshot, scene graph inspection, settings control, and rendering via HTTP API. Requires a browser with the editor open.
animation-basics
Animation theory covering the 12 principles of animation and timing guidance. Use when designing motion, choosing easing approaches, or improving animation quality.
add-tool
Generate a correctly formatted AgenticStack tool file ready to submit as a pull request.
setup-tool
Given what the user wants to add to their app, pick the right tool and explain how to get started — no comparison needed.
recommend-tool
Recommend the best developer tool for your requirements using AgenticStack data.