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 agentmods add skills/aethrox/doctrine/observabilitynpx skills add aethrox/doctrine --skill observabilitygit clone --depth 1 https://github.com/aethrox/doctrineWrote 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/aethrox/doctrine/observability)<a href="https://agentmods.dev/skills/aethrox/doctrine/observability"><img src="https://agentmods.dev/badge/skills/aethrox/doctrine/observability.svg" alt="Measured on agentmods" 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 | $0.00100 | $0.01120 |
| Opus 5 | $0.00050 | $0.00560 |
| Sonnet 5 | $0.00020 | $0.00224 |
| Haiku 4.5 | $0.00010 | $0.00112 |
Grade A, and why
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 4d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Observability
A service is not done until someone who has never read its code can answer "is it healthy right now" from its telemetry alone. That means structured logs that a platform can index and correlate, the four golden signals tracked per service, and an explicit SLO with an error budget, not "we'll notice if it breaks."
Phase 1: Structured logging
- Every log line is a structured record (JSON or the platform's structured format), not a hand-built string; fields are queryable and indexable; a concatenated string is only greppable.
- Every log line inside a request/job carries a correlation ID (trace ID / request ID) so a slow request, its trace, and its log lines can be joined without copy-pasting timestamps.
- Log levels mean something consistent across the codebase:
error= needs human attention,warn= degraded but self-recovering,info= significant state change (request completed, job started),debug= development-time detail, off by default in production. - Never log a secret, full payload, or PII field directly; log its presence or a redacted/hashed form (same redaction discipline as
diagnosing-bugsandsecure-coding). - Log the outcome, not just the attempt: "started X" without a matching "X succeeded / X failed (reason)" leaves a gap no dashboard can fill in later.
Phase 2: The four golden signals
Every service exposes these four, regardless of what else it tracks:
| Signal | What it measures | Typical source |
|---|---|---|
| Latency | time to serve a request: track success and failure latency separately, a fast failure skews the average down and hides a real slowdown | request duration histogram |
| Errors | rate of failed requests (5xx, exceptions, failed jobs) | error counter / request outcome |
| Traffic | demand on the system (requests/sec, queue depth, jobs/min) | request or throughput counter |
| Saturation | how full the constrained resource is (CPU, memory, connection pool, queue length) | resource utilization gauge |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 51 lines · 100 tokens per session scan A 21e8e935a757
observability is a skill published in the GitHub repository aethrox/doctrine (18 stars, last pushed 22d ago), licensed MIT. It adds 100 tokens to every session and 1,120 once invoked, about $0.0005 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 skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
ue-mcp-epic-routing
Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.
mcp-google-map-project
Project knowledge for developing and maintaining @cablate/mcp-google-map. Architecture, Google Maps API guide, GIS domain knowledge, and design decisions. Read this skill to onboard onto the project or make informed development decisions.
patsnap-maintain-payment
Patsnap Maintain Payment MCP for AI agents. A global patent search tool for freedom-to-operate assessment. It supports query-based, semantic, and image search, and can be combined with patent family, legal status, and analytics views to help users identify patents that may create FTO barriers more systematically. It…