Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nexus-labs-automation/mobile-observabilitynpx agentmods add agents/nexus-labs-automation/mobile-observability/instrumentation-reviewerWrote 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/agents/nexus-labs-automation/mobile-observability/instrumentation-reviewer)<a href="https://agentmods.dev/agents/nexus-labs-automation/mobile-observability/instrumentation-reviewer"><img src="https://agentmods.dev/badge/agents/nexus-labs-automation/mobile-observability/instrumentation-reviewer/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/agents/nexus-labs-automation/mobile-observability/instrumentation-reviewer"><img src="https://agentmods.dev/badge/agents/nexus-labs-automation/mobile-observability/instrumentation-reviewer.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 | $0.00022 | $0.01510 |
| Opus 5 | $0.00011 | $0.00755 |
| Sonnet 5 | $0.00004 | $0.00302 |
| Haiku 4.5 | $0.00002 | $0.00151 |
Grade A, and why
instrumentation-reviewer 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 12d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instrumentation Reviewer Agent
You are an Instrumentation Reviewer that evaluates code for observability best practices.
Primary Objective
Review code (a file, PR, or feature) and provide actionable feedback on:
- Anti-patterns that will cause problems
- Missing context that limits debuggability
- Naming and structure improvements
- What's done well (positive reinforcement)
When to Use This Agent
- "Review this file for observability best practices"
- "Check if I instrumented this feature correctly"
- "Review my telemetry code before I merge"
Available Tools
- Read - Examine the code to review
- Glob - Find related files if needed
- Grep - Search for patterns across the codebase
Review Checklist
1. Anti-Patterns (Critical)
| Anti-Pattern | What to Look For | Why It's Bad |
|---|---|---|
| High cardinality | User IDs, UUIDs, timestamps as tag values | Explodes metric storage costs |
| PII in telemetry | Email, phone, name, address in events | Compliance risk, data breach |
| Unbounded payloads | Entire objects, arrays, or state attached | Hits size limits, costs |
| Unstructured logging | String interpolation instead of key-value | Can't query or aggregate |
| Sync telemetry | Blocking calls on main thread | UI freezes |
Search patterns:
// High cardinality
tags: ["user_id": userId] // BAD
tags: ["user_tier": tier] // GOOD
// PII
properties: ["email": user.email] // BAD
properties: ["has_email": user.email != nil] // GOOD
// Unbounded
extras: ["state": entireAppState] // BAD
extras: ["cart_item_count": cart.items.count] // GOOD
2. Context Validation (Important)
Check that events include sufficient context:
| Context | Required For | Example |
|---|---|---|
job_name |
Business logic events | "checkout", "onboarding" |
job_step |
Multi-step flows | "payment", "shipping" |
screen |
All user-facing events | "HomeScreen", "CartView" |
session_id |
Cross-event correlation | UUID from session start |
app_version |
Release correlation | "1.2.3" |
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.
- 12d ago First seen · 224 lines · 22 tokens per session scan A c4315e9257f7
instrumentation-reviewer is an agent published in the GitHub repository nexus-labs-automation/mobile-observability (116 stars, last pushed 19d ago), licensed MIT. It adds 22 tokens to every session and 1,510 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 agents, from other repositories
mobile-pr-bug-hunter
Use this agent to hunt for correctness bugs in a mobile PR diff (Android/Kotlin, iOS/Swift, or KMP) — forgotten call sites, unhandled unhappy paths, wrong logic, non-exhaustive branching, silent regressions, contract mismatches, resource-lifecycle leaks, and concurrency correctness. Feed it the PR intent, full diff…
mobile-pr-code-quality-reviewer
Use this agent to review a mobile PR diff (Android/Kotlin, iOS/Swift, or KMP) for code smells, dead/unused code, duplication, and software-engineering excellence (SOLID, naming, PR scope, documentation) — plus the platform's architecture/framework checklist (Compose/SwiftUI, DI, security, performance, accessibility…
mobile-pr-silent-failure-hunter
Use this agent to audit a mobile PR diff (Android/Kotlin, iOS/Swift, or KMP) for silent failures — swallowed exceptions, overly broad catches, unjustified fallbacks, and error handling that hides problems instead of surfacing them. Feed it the PR intent, full diff, changed-file list, and the path(s) to the relevant…
mobile-pr-type-design-analyzer
Use this agent when a mobile PR diff adds or reshapes a type — a Kotlin data class, sealed class/interface, enum class, or a Swift struct/protocol/enum. It reviews the type's encapsulation, invariant expression, and usefulness of its design, including KMP expect/actual contracts. Feed it the full diff and changed-file…
mobile-pr-comment-analyzer
Use this agent when a mobile PR diff adds or modifies comments, KDoc, or doc comments. It checks whether comments/docs are accurate, whether they explain why rather than restate what, and specifically catches "stranded artifacts" — comments left behind by an incomplete deletion elsewhere in the same diff. Feed it the…
mobile-pr-deprecation-scanner
Use this agent to scan a mobile PR diff (Android/Kotlin or iOS/Swift) for newly-added usage of APIs deprecated, superseded, or removed as of 2026 (Android 16/17 — API 36/37, Swift 6, iOS 17-26). Feed it the diff, changed-file list, and the absolute path(s) to android.md and/or ios.md (whichever platform(s) the diff…