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/expensify/app/measure-telemetry-spannpx skills add Expensify/App --skill measure-telemetry-spangit clone --depth 1 https://github.com/Expensify/AppWrote 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/expensify/app/measure-telemetry-span)<a href="https://agentmods.dev/skills/expensify/app/measure-telemetry-span"><img src="https://agentmods.dev/badge/skills/expensify/app/measure-telemetry-span.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 | $0.00029 | $0.01328 |
| Opus 5 | $0.00015 | $0.00664 |
| Sonnet 5 | $0.00006 | $0.00266 |
| Haiku 4.5 | $0.00003 | $0.00133 |
Grade A, and why
measure-telemetry-span 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Measure Telemetry Span
Pattern: from repo root, run one command with a span name and platform → stdout is a small summary table (avg / min / max + sample ms list). The script measures whatever Git checkout is currently active: it never runs git checkout or otherwise switches branches. To compare this branch with main (or any other revision), check out each commit/branch in turn—or use two worktrees/clones—and run measure.sh separately, then compare the two printed summaries.
Command
.claude/skills/measure-telemetry-span/measure.sh <span-name> [runs] [platform] [--boot]
| Argument | Default | Description |
|---|---|---|
<span-name> |
— | Must match # @tag sentry-<span-name> on a flow under .claude/skills/agent-device/flows/tests/ (sentry-tagged QA scenarios live there; the script searches flows/ recursively, so flows/macros/ is also scanned for completeness). |
[runs] |
10 |
Measured replays after one warmup inside the script. |
[platform] |
ios |
ios or android — must match the simulator/emulator you use. |
--boot |
off | Before open, runs agent-device boot --platform <platform> so a simulator/emulator is started when nothing was connected (adb devices empty, etc.). |
To pick a specific Android AVD or iOS simulator, use the same global flags agent-device already supports (for example --device "Pixel_7_API_34") on boot and on later commands — either run agent-device boot --platform android --device "…" yourself before measure.sh, or rely on agent-device config (~/.agent-device/config.json). --boot inside this script only passes --platform through to boot.
Environment: APP_ID overrides app bundle (default com.expensify.chat.dev). If the flow declares # @param KEY …, set AD_KEY to pass -e KEY=VALUE to replay.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 70 lines · 29 tokens per session scan A 5c6714c57cd3
measure-telemetry-span is a skill published in the GitHub repository Expensify/App (5,016 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 1,328 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
react-native-ease-refactor
Scan for Animated/Reanimated code and migrate to EaseView.