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 joao-aires/agent-skills-public --skill python-ai-observabilitygit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/python-ai-observability)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/python-ai-observability"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/python-ai-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/skills/joao-aires/agent-skills-public/python-ai-observability"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/python-ai-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 | $0.00054 | $0.01140 |
| Opus 5.5 | $0.00022 | $0.00456 |
| Sonnet 5.5 | $0.00011 | $0.00228 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
python-ai-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 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instrument Python AI execution
Use the accepted task/service outcomes and operating constraints. Seek available reliability/observability and AI-evaluation expertise for signal meaning and quality boundaries; keep those outcomes explicit when specialist guidance is absent. This skill owns Python AI instrumentation and export integration. Collector/backend deployment, service SLO design and quality scoring remain separate responsibilities.
Establish instrumentation ownership
Inspect existing Python SDKs, framework/provider integrations, tracer/meter providers, exporter configuration and process lifecycle. Reuse the application telemetry owner rather than initializing another global provider or instrumenting the same model call twice. Select compatible locked API/SDK, exporter and instrumentor versions; provider/framework wrappers need support for the actual installed versions and execution path.
Place application spans around work whose completion matters to the user or operator, then connect provider, retrieval and tool calls beneath that work where supported. A span should have a recognizable beginning and end and record whether its own operation succeeded. Ending a parent request while background work continues requires an explicit lifecycle and supported context propagation, rather than keeping an unrelated span open indefinitely.
Choose manual OpenTelemetry spans for application task boundaries and supported automatic instrumentation for concrete provider/framework calls when useful. Follow Python instrumentation and the selected instrumentor's primary documentation. A direct SDK call, a framework graph and a remote harness have different visibility; inspect supported hooks rather than claiming hidden remote steps are traced.
For application-owned manual setup, use the compatible SDK's Resource and TracerProvider, a BatchSpanProcessor and the selected OTLPSpanExporter; application spans use trace.get_tracer() and its context-managed span API. Libraries obtain the configured tracer rather than installing a provider. Match startup/flush/shutdown to the actual worker/server lifecycle.
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.
- yesterday Changed · +18 lines f54bda1ebe00
- 2d ago First seen · 47 lines · 54 tokens per session scan A 6d3f94881d69
python-ai-observability is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 1,140 once invoked, about $0.0002 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 2026-10-20.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…