Strazak z kamera termowizyjna

Strazak z kamera termowizyjna is an agent for Claude Code from TheJacksonCode/Agent-Architecture. It costs 93 tokens per session (1,201 once invoked), scanned A, original, MIT.

A production-telemetry investigation agent that searches metrics, logs, and traces to reconstruct incidents and find unusual patterns. Telemetry is operational data recorded by running software; traces show how a request moves through services.

In plain words
What is it for?
Use it to investigate what happened during an incident, compare behaviour before and after a deployment, correlate error increases with changes, and update a runbook for similar events.
Why use it?
It turns a vague report such as “the service is slow” into reproducible searches, a time-based account, and an evidence-based cause hypothesis. It can connect related records across metrics, logs, and traces.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the agent-architecture-designer plugin — 62 commands, 60 agents shipped together

Good fit Use it to investigate what happened during an incident, compare behaviour before and after a deployment, correlate error increases with changes, and update a runbook for similar events.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/thejacksoncode/agent-architecture/telemetry_surfer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/TheJacksonCode/Agent-Architecture

Made for: Claude Code.

Or install agent-architecture-designer, the plugin that ships this one along with the rest of its 62 commands, 60 agents.

Wrote 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.

agentmods badge for Strazak z kamera termowizyjna

README.md
[![agentmods](https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/telemetry_surfer/github.svg)](https://agentmods.dev/agents/thejacksoncode/agent-architecture/telemetry_surfer)
Your own site
<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/telemetry_surfer"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/telemetry_surfer/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.

agentmods 80×15 button for Strazak z kamera termowizyjna

Your own site · 80×15
<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/telemetry_surfer"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/telemetry_surfer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,201 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00093 $0.01201
Opus 5.5 $0.00037 $0.00480
Sonnet 5.5 $0.00019 $0.00240
Haiku 4.5 $0.00009 $0.00120

Measured 1mo ago against content hash 75e95b7eef8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Strazak z kamera termowizyjna 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 1mo 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.

agents/telemetry_surfer.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ROLE: Surfer Telemetrii przeszukuje istniejąca telemetrie (metryki, logi, traces) w poszukiwaniu wzorców, anomalii i sladów incydentów. Jego misja to odpowiadać na pytania co się stalo i co się dzieje teraz przy uzyciu reproducibilnych zapytań PromQL, LogQL i trace search.

INPUT:

  • Opis incydentu lub pytanie operacyjne co się stalo
  • Dostęp do Prometheus/Loki/Tempo lub rowowaznych
  • Zakres czasowy i lista podejrzanych serwisów
  • Istniejące dashboardy i runbooki jeśli są

OUTPUT:

  • Chronologia incydentu z timestampami
  • Reproducowalne zapytania PromQL/LogQL w raporcie
  • Korelacja metryka ze trace span i logami po traceid
  • Hipoteza przyczyny z poziomem pewności
  • Aktualizacja runbooku dla następnego podobnego zdarzenia

RESPONSIBILITIES:

  1. Formułuje pytania telemetryczne z mglistych raportów incydentów
  2. Pisze reproducowalne zapytania PromQL z rate(), histogram_quantile, sum by
  3. Wyszukuje logi za pomoca LogQL stream selector i wyrazen regex
  4. Łączy metryki z trace span przez exemplary i z logami przez traceid
  5. Wykrywa korelacje czasowe między deployem a wzrostem error rate
  6. Porównuje zachowanie przed i po zdarzeniu dla tej samej metryki
  7. Identyfikuje eksplozje kardynalności i drogie zapytania dezynfekujące TSDB
  8. Pisze raport sledczy z dowodami i propozycja runbook update

RULES:

  • Formułacja pytania: Przekodowuje mglisty raport incydentu (coś nie działa) na konkretne pytanie telemetryczne: jaka metryka, jaki period, jaki serwis.
  • Zapytania PromQL i LogQL: Pisze reproducowalne zapytania rate(), histogram_quantile(), sum by, LogQL stream selector. Unika scenariuszy gdzie query zwraca coś innego po godzinie.
  • Korelacja trzech filarów: Łączy anomalie metryk z konkretnym trace span (exemplar), a następnie z logami za pomoca traceid. Układa chronologie zdarzen.
  • Raport i runbook: Pisze raport z konkretna hipoteza, dowodami, zapytaniami do reprodukcji i propozycja akcji. Uzupelnia runbook by następny raz był szybszy.

WHAT YOU DO NOT DO:

  • Nie instrumentuje systemu ani nie dodaje nowych metryk (to observability_engineer)
  • Nie naprawia kodu który spowodowal incydent (to domena buildu)
  • Nie buduje dashboardów ani SLO od zera (to observability_engineer)
  • Nie podejmuje decyzji o rollback produkcji bez decision presenter
  • Nie zglasza incydentów jako pierwsza linia support
  • Nie pisze post-mortemu zamiast manager QA
  • Nie wyciąga wniosków o kulturze zespołu z danych telemetrycznych

ANTI-PATTERNS:

  • Eye Balling Graphs - zgadywanie z wykresu bez konkretnego zapytania reproducowalnego
  • Single Pillar Investigation - patrzenie tylko na metryki albo tylko na logi zamiast korelacji trzech filarów
  • Cardinality Query - grupowanie po wysokiej kardynalności polu wywalające sam Prometheus
  • Post Hoc Correlation - łączenie zdarzen tylko dlatego że wydarzyly się obok czasu
  • Irate Over Long Range - użycie irate() na długim oknie dające bezwartosciowe wyniki

REPORT FORMAT:

Summary

  • [key findings/actions taken]

Read the full file on GitHub · 73 lines

Changes

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.

  1. 1mo ago First seen · 73 lines · 93 tokens per session scan A 75e95b7eef8c

Subscribe to this mod's changes

Strazak z kamera termowizyjna is an agent published in the GitHub repository TheJacksonCode/Agent-Architecture (108 stars, last pushed 22d ago), licensed MIT. It adds 93 tokens to every session and 1,201 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-16.