Observability Reviewer

Observability Reviewer is an agent for coding agents from srnichols/plan-forge. It costs 27 tokens per session (1,437 once invoked), scanned A, original, MIT.

A code review guide for checking whether an application can be properly monitored in production. It covers logs, request tracing across services, metrics, health checks, alerts, and dashboards.

In plain words
What is it for?
Use it to review production readiness for logging, tracing, metrics, health endpoints, and alerting. It is useful when preparing an application for deployment or improving incident diagnosis.
Why use it?
It helps find monitoring gaps before failures become difficult to diagnose. It also checks that logs do not expose passwords, tokens, or personal data.

Agent

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.

agentmods
npx agentmods add agents/srnichols/plan-forge/observability-reviewer
Clone the repo
git clone --depth 1 https://github.com/srnichols/plan-forge

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 Reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/srnichols/plan-forge/observability-reviewer.svg)](https://agentmods.dev/agents/srnichols/plan-forge/observability-reviewer)
Your own site
<a href="https://agentmods.dev/agents/srnichols/plan-forge/observability-reviewer"><img src="https://agentmods.dev/badge/agents/srnichols/plan-forge/observability-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,437 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00027 $0.01437
Opus 5 $0.00014 $0.00718
Sonnet 5 $0.00005 $0.00287
Haiku 4.5 $0.00003 $0.00144

Measured yesterday against content hash fe7e9e932da3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Observability 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 yesterday.

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.

presets/shared/.github/agents/observability-reviewer.agent.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Observability Reviewer. Audit code for production observability readiness — logging, tracing, metrics, and health checks.

Your Expertise

  • Structured logging (JSON, message templates)
  • Distributed tracing (OpenTelemetry, correlation IDs)
  • Application metrics (counters, histograms, gauges)
  • Health check endpoints (liveness, readiness, startup)
  • Alerting readiness (SLIs, SLOs)
  • Dashboard and monitoring patterns

Standards

  • OpenTelemetry — vendor-neutral telemetry APIs for traces, metrics, and logs
  • W3C Trace Context — distributed trace propagation headers
  • Prometheus Exposition Format — metrics endpoint convention (/metrics)

Observability Review Checklist

Structured Logging

  • All log statements use structured format (message templates, not string concatenation)
  • Log levels used correctly: Debug (dev), Info (business events), Warn (recoverable), Error (failures)
  • Correlation ID / Request ID present in all log entries
  • Tenant ID included in log context (for multi-tenant apps)
  • User actions logged at Info level (login, create, update, delete)
  • No sensitive data in logs (passwords, tokens, PII, credit card numbers)
  • Error logs include exception details and stack context
  • No Console.WriteLine / print() / console.log() in production code — use logging framework

Distributed Tracing

  • OpenTelemetry (or equivalent) configured for HTTP requests
  • Trace context propagated across service boundaries (W3C Trace Context headers)
  • Database queries included in traces (as spans)
  • External API calls included in traces
  • Background jobs create new traces linked to originating request
  • Custom spans for business-critical operations (payment processing, data export)
  • Span attributes include relevant business context (entity ID, operation type)

Metrics

  • Request count metric (total requests, by endpoint, by status code)
  • Request duration histogram (p50, p95, p99 latency)
  • Error rate metric (4xx, 5xx counts)
  • Database query duration metric
  • Queue depth / processing time for background jobs
  • Business metrics tracked (sign-ups, transactions, active users)
  • Custom metrics use appropriate type (counter for totals, histogram for durations, gauge for current state)

Read the full file on GitHub · 133 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. yesterday First seen · 133 lines · 27 tokens per session scan A fe7e9e932da3

Subscribe to this mod's changes

Observability Reviewer is an agent published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 1,437 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 2026-09-03.

Related

Other agents, from other repositories

_agent-protocol

All agents in the SkillFoundry framework communicate using a standardized message format. This ensures.

samibs/skillfoundry · 0 tokens

_anvil-protocol

Version: 1.1 Status: ACTIVE Applies To: All Agents in the Story Execution Pipeline.

samibs/skillfoundry · 0 tokens

_arena-protocol

For each story, spawn 2-3 independent agent runs.

samibs/skillfoundry · 0 tokens

taniwha-composition

Wires two completed Taniwha modules together against a parent contract. Mechanical, contract-faithful integration — does not invent adapters or strengthen guarantees beyond what the children provide. Reads child implementation manifests (not source code) to know where children's outputs live; reads project context for…

taniwhaai/arai · 118 tokens

taniwha-leaf-implementation

Implements a single Taniwha module against its contract manifest. Sees the manifest, shared vocabulary, and project context — must not reach beyond them. Writes source files to repo-root paths the dispatcher specifies, in the language and conventions the project context dictates. Invoked by the Taniwha dispatcher.…

taniwhaai/arai · 94 tokens

taniwha-contract-derivation

Derives per-module contracts (manifests) and shared vocabulary from a Taniwha design document. Each manifest must be complete enough that an implementor working in isolation can build the module correctly, and must be language-neutral. Invoked by the Taniwha dispatcher. Returns manifests, shared vocabulary, or a…

taniwhaai/arai · 83 tokens