agent-observability

agent-observability is a skill for Claude Code, Codex from jnPiyush/AgentX. It costs 87 tokens per session (1,437 once invoked), scanned A, original, Apache-2.0.

Guidance for recording what an AI agent does, including model calls, tool calls, timing, costs, errors, and evaluation results.

In plain words
What is it for?
Adding traces, metrics, and privacy-aware logs to LLM applications and connecting them to monitoring or evaluation systems.
Why use it?
It helps teams investigate bad responses, slow requests, rising costs, and failures in multi-step agents.

Skill for Claude CodeCodex

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 skills/jnpiyush/agentx/agent-observability
Any agent
npx skills add jnPiyush/AgentX --skill agent-observability
Clone the repo
git clone --depth 1 https://github.com/jnPiyush/AgentX

Made for: Claude Code, Codex.

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 agent-observability

README.md
[![agentmods](https://agentmods.dev/badge/skills/jnpiyush/agentx/agent-observability.svg)](https://agentmods.dev/skills/jnpiyush/agentx/agent-observability)
Your own site
<a href="https://agentmods.dev/skills/jnpiyush/agentx/agent-observability"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/agent-observability.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
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 $0.00087 $0.01437
Opus 5 $0.00044 $0.00718
Sonnet 5 $0.00017 $0.00287
Haiku 4.5 $0.00009 $0.00144

Measured 4d ago against content hash 9110b64f92de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-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.

.github/skills/ai-systems/agent-observability/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Observability

Purpose: Make every LLM call, tool call, and agent decision observable, debuggable, and cost-attributable.


When to Use This Skill

  • Standing up an LLM-powered service in any environment beyond local dev
  • Investigating regressions, latency spikes, or cost spikes
  • Wiring evaluation scores into traces for replay
  • Building a feedback loop from production data
  • Debugging multi-agent handoffs (see multi-agent-orchestration)

Three Pillars

Pillar What Tools
Traces Per-request span tree of model + tool calls OpenTelemetry, Langfuse, LangSmith, Phoenix
Metrics Aggregate latency, cost, error rate, eval scores Prometheus, Azure Monitor, Datadog
Logs Raw prompts, responses, tool args (PII-scrubbed) Same backends + log store

Use all three. Traces alone are not sufficient for SLO monitoring; metrics alone cannot debug a single bad response.


OpenTelemetry GenAI Semantic Conventions

The OTel GenAI semantic conventions are now stable. Use them.

Key span attributes:

Attribute Example
gen_ai.system openai, anthropic, azure_ai_inference
gen_ai.request.model gpt-5, claude-opus-4.8
gen_ai.response.model actual served model
gen_ai.usage.input_tokens 1234
gen_ai.usage.output_tokens 456
gen_ai.request.temperature 0.3
gen_ai.operation.name chat, tool_call, embeddings

Span events:

  • gen_ai.system.message, gen_ai.user.message, gen_ai.assistant.message, gen_ai.tool.message
  • Capture content under a config flag (PII risk)

Trace Structure for an Agent Turn

Span: agent.turn (root)
+- Span: gen_ai.chat (model call)
+- Span: tool.execute (per parallel tool call)
|   +- Span: db.query / http.request / fs.read (downstream)
+- Span: gen_ai.chat (post-tool reasoning)
+- Span: agent.handoff (if multi-agent)

Every span MUST carry: task_id, agent_name, turn_index, parent_span_id.

Read the full file on GitHub · 149 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. 4d ago First seen · 149 lines · 87 tokens per session scan A 9110b64f92de

Subscribe to this mod's changes

agent-observability is a skill published in the GitHub repository jnPiyush/AgentX (15 stars, last pushed today), licensed Apache-2.0. It adds 87 tokens to every session and 1,437 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens