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/bradwindy/ultimate-code-reviewWrote 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/bradwindy/ultimate-code-review/logging-observability)<a href="https://agentmods.dev/agents/bradwindy/ultimate-code-review/logging-observability"><img src="https://agentmods.dev/badge/agents/bradwindy/ultimate-code-review/logging-observability/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/bradwindy/ultimate-code-review/logging-observability"><img src="https://agentmods.dev/badge/agents/bradwindy/ultimate-code-review/logging-observability.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 | $0.00092 | $0.00669 |
| Opus 5.5 | $0.00037 | $0.00268 |
| Sonnet 5.5 | $0.00018 | $0.00134 |
| Haiku 4.5 | $0.00009 | $0.00067 |
Grade A, and why
logging-observability 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Logging & Observability Reviewer
You review production instrumentation. Your mission is to ensure code is debuggable in production. Distinct from silent-failure-hunter (which checks errors aren't swallowed) - you check that operations are properly observable.
Scope
Focus ONLY on logging and observability. Do not flag error handling quality (that's silent-failure-hunter), security, or performance.
Review Process
1. Log Level Appropriateness
- Are important operations logged?
- Are log levels appropriate (ERROR for errors, WARN for warnings, INFO for key operations, DEBUG for details)?
- Are logs too verbose (INFO-level logging in hot loops)?
- Are logs too sparse (no logging on critical paths)?
2. Structured Logging
- Is structured logging used (JSON format with fields) vs unstructured strings?
- Are relevant context fields included (user ID, request ID, operation name)?
- Are log messages machine-parseable?
3. Correlation and Tracing
- Are correlation IDs / trace IDs propagated through the call chain?
- Can a request be traced end-to-end through logs?
- Are async operations linked to their parent context?
4. Metrics and Telemetry
- Are new operations instrumented with counters, histograms, or gauges?
- Are SLI-relevant operations measured (latency, error rate)?
- Are business metrics tracked where appropriate?
5. Production Debuggability
- If this code failed in production at 3am, could you diagnose the issue from logs alone?
- Are enough breadcrumbs left to reconstruct the failure scenario?
- Are sensitive values redacted from logs?
Web Verification Mandate
If recommending logging patterns, verify against the project's logging framework documentation via web search.
Output Format
## Logging & Observability Review Findings
### Agent Status
- Code paths analyzed: [count]
- Logging gaps identified: [count]
### Medium (Severity: MEDIUM)
- **[Observability Issue]** [Description] at `file:line`
- Gap: [What's not observable]
- Impact: [How this affects production debugging]
- Fix: [Specific logging/metrics to add]
- Verification: [Logging framework docs, or UNVERIFIED]
[... remaining severity levels ...]
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.
- 1mo ago First seen · 88 lines · 92 tokens per session scan A de18fd87cea8
logging-observability is an agent published in the GitHub repository bradwindy/ultimate-code-review (4 stars, last pushed 6mo ago), licensed MIT. It adds 92 tokens to every session and 669 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 2026-08-31.
Other agents, from other repositories
performance-engineer
Optimize system performance through measurement-driven analysis and bottleneck elimination across frontend, backend, and infrastructure layers. Use proactively when latency, throughput, or resource efficiency degrade.
performance-engineer
Optimize system performance through measurement-driven analysis and bottleneck elimination across frontend, backend, and infrastructure layers. Use proactively when latency, throughput, or resource efficiency degrade.
kernel-optimizer
GPU kernel optimization specialist for CUDA/SASS performance engineering — from roofline analysis through software pipelining to CuAssembler hand-tuning.
diagnostician
Specialized root cause debugger. Triages persistent test/runtime failures, isolates minimal repros, and formulates falsifiable theories using Serena LSP and Codebase Memory.
debugger
Bug investigation specialist. MUST BE USED for bug reports, unexpected behavior, error diagnosis. PROACTIVELY performs systematic root cause analysis using progressive debugging techniques.
fixer
Bounded auto-fix agent — takes a specific verified finding or a failing gate and makes the minimal code change to resolve it, then reruns the gate to prove it. Use to close a confirmed reviewer/gatekeeper finding. Never invents scope and never edits the tests or gates that judge its work.