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/querynpx skills add agenkin/telemetrydeck-analytics --skill querygit 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 | $0.00047 | $0.00364 |
| Opus 5 | $0.00023 | $0.00182 |
| Sonnet 5 | $0.00009 | $0.00073 |
| Haiku 4.5 | $0.00005 | $0.00036 |
Grade A, and why
query 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
Query
Run raw TQL against the current app. Two ways:
(a) Inline JSON from $ARGUMENTS — pipe it to tdq query -:
echo '$ARGUMENTS' | tdq query -
(b) JSON file path — pass the path directly:
tdq query $ARGUMENTS
Pick (b) if $ARGUMENTS looks like a file path, else (a).
Writing the TQL
Before writing the JSON, read skills/analytics/tql/index.md in this plugin to route to the right sub-reference (filters, aggregators, intervals, funnel, retention, recipes, etc.). Do not try to recall TQL syntax from memory — the progressive-disclosure tree is there for a reason.
Rules that always apply:
- Set
"filter": { "__auto_app_and_test_mode_filter__": true }unless you need a custom filter (in which case include theappID+isTestMode=falseselectors yourself). - Every query needs
queryTypeandgranularity. - Prefer
userCount/thetaSketchover deprecatedcardinality.
If the user's first query returns (no rows), re-run with --raw to see whether the result is genuinely empty or the parser dropped it:
tdq query /tmp/q.json --raw 2>/tmp/raw.json
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 · 38 lines · 47 tokens per session scan A 474e97df399d
query is a skill published in the GitHub repository agenkin/telemetrydeck-analytics (2 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 364 once invoked, about $0.0002 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.