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.
git clone --depth 1 https://github.com/btachinardi/churchWrote 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/commands/btachinardi/church/observability-crusade)<a href="https://agentmods.dev/commands/btachinardi/church/observability-crusade"><img src="https://agentmods.dev/badge/commands/btachinardi/church/observability-crusade/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/commands/btachinardi/church/observability-crusade"><img src="https://agentmods.dev/badge/commands/btachinardi/church/observability-crusade.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 | $0.00030 | $0.04040 |
| Opus 5 | $0.00015 | $0.02020 |
| Sonnet 5 | $0.00006 | $0.00808 |
| Haiku 4.5 | $0.00003 | $0.00404 |
Grade A, and why
observability-crusade 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 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.
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 — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Observability Crusade
"In the beginning, there was darkness upon the codebase. And the Observability Purists said: LET THERE BE LIGHT."
This command orchestrates a multi-squad crusade to eliminate observability sins and bring full instrumentation to your codebase.
Command Invocation
# Survey darkness only (report mode)
/observability-crusade
# Survey specific scope
/observability-crusade --scope api
/observability-crusade --scope web
# Survey and apply fixes
/observability-crusade --illuminate
# Target specific directory
/observability-crusade apps/api/src/domains/orders
/observability-crusade apps/api/src/domains/orders --illuminate
The Four Phases
Phase 1: The Darkness Survey
First, we scan the codebase to identify every sin against observability:
Sins to detect:
- Empty Catch Blocks:
catch (e) {},catch {}, catch blocks with only comments - Bare Console Calls:
console.log,console.error,console.warnin non-test files - Untraced Endpoints: API controllers/routes with no logging
- Untraced External Calls: HTTP calls, database queries without timing/logging
- Missing Correlation IDs: No middleware, no propagation
- Unstructured Logs: String concatenation instead of structured objects
- Missing Health Checks: No
/healthendpoint - Swallowed Errors: Catch and return null/undefined without logging
- Missing Business Metrics: No counters or histograms for business operations
- Error Responses Without Context: Throwing exceptions without logging details
Scan commands:
# Empty catch blocks
rg 'catch\s*\([^)]*\)\s*\{\s*\}' --type ts --type tsx
# Bare console calls (exclude test files)
rg 'console\.(log|error|warn|info|debug)' --type ts --type tsx -g '!*.spec.ts' -g '!*.test.ts' -g '!*.e2e.ts'
# Catch blocks with only comments
rg 'catch.*\{[^}]*//[^}]*\}' --type ts --type tsx
# Missing correlation ID usage in services
rg 'logger\.(info|error|warn)' -A 2 --type ts | rg -v 'correlationId'
# Unstructured string concat logs
rg "logger\.(info|error|warn)\(['\"].*\+.*\)" --type ts
# Missing health check endpoints
rg -L '@Get.*health' apps/api
# Promise without catch
rg 'await\s+\w+\(.*\)' --type ts -g '!*.spec.ts' | rg -v 'try|catch'
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.
- 10d ago First seen · 534 lines · 0 tokens per session scan A d50c7db3c438
observability-crusade is a command published in the GitHub repository btachinardi/church (58 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 4,040 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 2026-08-30.
Other commands, from other repositories
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
fix
Universal debugging and fix application with semantic code analysis.
doctor
Badi configuration validation. Checks all Badi components and produces a diagnostic report.
http-service
Build, review or debug a Bun HTTP service. Loads the http-service skill, then works the task through its workflow.
gh-issue-use-cypress
Like /gh-issue-use-browser, but pinned to the Cypress MCP — use when your project runs the Cypress MCP for browser automation. Example — /gh-issue-use-cypress "Composer > Save" saving toasts failure but the record persists.