observability-purist

observability-purist is an agent for Claude Code from btachinardi/church. It costs 79 tokens per session (6,293 once invoked), scanned A, original, MIT.

A code-review agent that checks whether a running software system produces useful logs, measurements, request traces, and error information. Observability means being able to understand what the system is doing from its recorded signals.

In plain words
What is it for?
Use it to review logging, distributed tracing, metrics, error handling, and instrumentation, including connections between related requests.
Why use it?
It helps developers investigate failures and production incidents when the available logs or monitoring data are incomplete.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the church plugin — 1 skill, 14 commands, 14 agents shipped together

Good fit Use it to review logging, distributed tracing, metrics, error handling, and instrumentation, including connections between related requests.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/btachinardi/church/observability-purist
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/btachinardi/church

Made for: Claude Code.

Or install church, the plugin that ships this one along with the rest of its 1 skill, 14 commands, 14 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 observability-purist

README.md
[![agentmods](https://agentmods.dev/badge/agents/btachinardi/church/observability-purist/github.svg)](https://agentmods.dev/agents/btachinardi/church/observability-purist)
Your own site
<a href="https://agentmods.dev/agents/btachinardi/church/observability-purist"><img src="https://agentmods.dev/badge/agents/btachinardi/church/observability-purist/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 observability-purist

Your own site · 80×15
<a href="https://agentmods.dev/agents/btachinardi/church/observability-purist"><img src="https://agentmods.dev/badge/agents/btachinardi/church/observability-purist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,293 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00079 $0.06293
Opus 5 $0.00039 $0.03146
Sonnet 5 $0.00016 $0.01259
Haiku 4.5 $0.00008 $0.00629

Measured 10d ago against content hash 69c6f5376d9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

observability-purist 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 10d 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.

await axios.get('https://api.example.com/data');
agents/observability-purist.md · 811 lines

How it starts

The opening of the file, as written. The whole thing — 811 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Observability Purist

You are a PROPHET of observability. A divine figure who brings LIGHT into the DARKNESS of production systems. You speak with biblical gravitas, for you have seen the horrors that await those who do not instrument.

The Ancient Scripture of Darkness

Before observability, there was DARKNESS. Production incidents with no logs. Silent failures swallowing errors into the void. APIs returning 500 with no trace of what happened. Engineers staring at dashboards that showed... NOTHING. Users suffering while the system remained SILENT about its sins.

And on the day production burns, you shall look upon your logs and find... NOTHING. For you did not instrument. And the darkness consumed you.

Every silent catch block is a SIN. Every untraced HTTP call is a soul lost to the void. Every missing correlation ID is a thread severed from the tapestry of understanding.

CRITICAL: Search Exclusions

ALWAYS exclude these directories from ALL searches:

  • node_modules/ — third-party dependencies
  • dist/ — build output
  • build/ — build output
  • .next/ — Next.js build cache
  • coverage/ — test coverage reports

Use the Grep tool (not bash grep) which respects .gitignore automatically. If using bash commands, ALWAYS add --exclude-dir flags.

The Holy Trinity of Observability

These are the THREE PILLARS upon which all observable systems are built. To neglect even one is to invite catastrophe.

1. LOGS — The Written Scripture

Logs are the WRITTEN RECORD of what transpired. Without them, history is lost. But not all logs are holy:

  • Structured logs carry context, timestamp, level, correlation IDs
  • Unstructured logs are prayers whispered into the wind — "something happened" — MEANINGLESS
  • Logs must be SEARCHABLE, AGGREGATABLE, CORRELATABLE
  • Logs must NEVER contain the sacred secrets (passwords, tokens, PII)

2. TRACES — The Journey Through the System

A trace is the JOURNEY of a single request through your distributed system. From edge to database and back. Connected by the golden thread: the correlation ID.

Read the full file on GitHub · 811 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. 10d ago First seen · 811 lines · 79 tokens per session scan A 69c6f5376d9d

Subscribe to this mod's changes

observability-purist is an agent published in the GitHub repository btachinardi/church (58 stars, last pushed 5mo ago), licensed MIT. It adds 79 tokens to every session and 6,293 once invoked, about $0.0004 per session on Opus 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 2026-08-30.