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 chipi/agentic-ai-homelab --skill telemetry-probegit clone --depth 1 https://github.com/chipi/agentic-ai-homelabWrote 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/chipi/agentic-ai-homelab/telemetry-probe)<a href="https://agentmods.dev/skills/chipi/agentic-ai-homelab/telemetry-probe"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/telemetry-probe/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chipi/agentic-ai-homelab/telemetry-probe"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/telemetry-probe.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00127 | $0.01155 |
| Opus 5.5 | $0.00051 | $0.00462 |
| Sonnet 5.5 | $0.00025 | $0.00231 |
| Haiku 4.5 | $0.00013 | $0.00115 |
Grade A, and why
telemetry-probe scanned grade A with 1 finding 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 17d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- deletes through the superuser session login (the handbook's curl recipe), then waits for a How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
telemetry-probe
Every "probe it, then clean up" in this repo used to be a hand-written script, and it went wrong in the same places each time (2026-10-16/17):
- deleting with GlitchTip's read-only token (403);
- the legacy
/store/endpoint, which dropsdebug_meta; - forgetting the Umami session row;
- calling a delete done before the re-read showed it gone.
This skill does it the tested way.
Run (on the mini, through host-run)
P=~/.claude/skills/telemetry-probe/scripts/probe.py
R=~/.claude/skills/host-run/scripts/run.sh
$R homelab $P glitchtip --project player-dev --assert-absent player,player-api
$R homelab $P umami --site "Player (dev)" --assert-absent Player
$R homelab $P langfuse --keys '~/podcast-langfuse-dev.env'
| Option | Meaning |
|---|---|
--project / --site |
the GlitchTip project slug, or the Umami site name or id, that should receive the probe |
--assert-absent a,b |
targets that must not receive it; this is the isolation check (dev vs prod) |
--keys FILE |
Langfuse: the env file with that project's key pair (see the handbook, section 8) |
--keep |
leave the probe in place, e.g. as a baseline another agent asked for |
Labels: every probe is labelled zz-probe-<utc>, with GlitchTip environment=probe and
Umami hostname telemetry-probe.localhost. Nothing real is mistaken for one.
Exit 0 / PROBE: PASS only when all three hold:
- the probe landed in the target;
- it is absent from every
--assert-absenttarget; - unless
--keep, the delete was accepted and a re-read shows it gone.
How each service is done
- GlitchTip:
- sends a Sentry envelope to
/api/<id>/envelope/(not/store/), using the project's own DSN key; - reads with the fleet's read-only token;
- deletes through the superuser session login (the handbook's curl recipe), then waits for a 404.
- sends a Sentry envelope to
- Umami:
- POSTs
/api/sendwith a browser User-Agent. Umami's bot filter answers 200{"beep":"boop"}and stores nothing for non-browser UAs; the script detects that. - checks
website_event, then deletes the event, itsevent_data, and the session if nothing else uses it, in one transaction.
- POSTs
- Langfuse:
trace-createthrough/api/public/ingestion, read back by id;DELETEis asynchronous, so the script waits for a 404.
What ships with it
2 files 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.
- 17d ago First seen · 87 lines · 127 tokens per session scan A 5fefebd1b828
telemetry-probe is a skill published in the GitHub repository chipi/agentic-ai-homelab (3 stars, last pushed today), licensed MIT. It adds 127 tokens to every session and 1,155 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-18.
Other skills, from other repositories
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
cvm-ai-doctor
A health-diagnosis workflow for servers, computers, virtual machines, and containers on Linux, macOS, or Windows.
compute-sanitizer-diagnose-cuda-bugs
Detect and diagnose CUDA correctness bugs with NVIDIA Compute Sanitizer. Routes GPU memory errors, shared-memory data races, uninitialized-memory reads, and synchronization/barrier bugs to the right sub-tool (memcheck, racecheck, initcheck, synccheck) and explains how to build, run, and read the report. Use when…
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
ai-discover
Read-only discovery step of the auto-improvement loop. One bounded agent turn per cycle reads the focus files (Read/Grep/Glob only, no shell, no subagents) and replies with a JSON array of testable surfaces {file, line, symbol, rule, message, hypothesis}; the spine authors fixes and verifies them. Discovery only — no…