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.
npx skills add hoangatg/ai-agent-toolkit --skill observability-engineergit clone --depth 1 https://github.com/hoangatg/ai-agent-toolkitWrote 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/skills/hoangatg/ai-agent-toolkit/observability-engineer)<a href="https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/observability-engineer"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/observability-engineer/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/skills/hoangatg/ai-agent-toolkit/observability-engineer"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/observability-engineer.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 | $0.00036 | $0.00888 |
| Opus 5 | $0.00018 | $0.00444 |
| Sonnet 5 | $0.00007 | $0.00178 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
observability-engineer 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 7d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Observability Engineer
If you can't see it, you can't fix it. If you can't measure it, you can't improve it.
1. Three Pillars
| Pillar | Purpose | Tools |
|---|---|---|
| Metrics | What's happening (numbers) | Prometheus, Datadog, CloudWatch |
| Logging | Why it happened (events) | ELK, Loki, CloudWatch Logs |
| Tracing | How it happened (flow) | Jaeger, Tempo, X-Ray |
2. Metrics Design
RED Method (Services)
| Metric | Measures |
|---|---|
| Rate | Requests per second |
| Errors | Failed requests per second |
| Duration | Latency distribution (p50, p95, p99) |
USE Method (Resources)
| Metric | Measures |
|---|---|
| Utilization | % time resource is busy |
| Saturation | Queue depth / backlog |
| Errors | Error count |
Golden Signals
| Signal | Question |
|---|---|
| Latency | How long do requests take? |
| Traffic | How much demand? |
| Errors | What's failing? |
| Saturation | How full is the system? |
3. Logging Best Practices
| Principle | Application |
|---|---|
| Structured | JSON format, not free text |
| Leveled | DEBUG, INFO, WARN, ERROR, FATAL |
| Contextual | Include requestId, userId, traceId |
| Sampling | High-volume logs: sample, don't log all |
| Retention | Define tiered retention policies |
What to Log
| ✅ Do Log | ❌ Don't Log |
|---|---|
| Request/response metadata | Sensitive data (PII, secrets) |
| Error details with stack | Successful health checks |
| State transitions | Every database query |
| Authentication events | Request/response bodies (usually) |
4. Alerting Strategy
Alert Design
| Principle | Application |
|---|---|
| Symptom-based | Alert on user impact, not causes |
| Actionable | Every alert must have a runbook |
| Tiered severity | P1 (page now) → P4 (review later) |
| Low noise | Tune to avoid alert fatigue |
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.
- 7d ago First seen · 130 lines · 36 tokens per session scan A d5d373f4042d
observability-engineer is a skill published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 888 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 2026-09-03.
Other skills, from other repositories
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
issue-root-resolution
Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.
rdd-defect-workflow
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
incident-response
Incident management lifecycle — triage, communicate, mitigate, postmortem. Three modes — new (start incident), update (status update), postmortem (blameless RCA report).
ctxo-safe-edit
Use BEFORE editing, renaming, or deleting any function, class, or method, to avoid breaking dependents.