agent-observability: Instructions file for Claude Code

CLAUDE.md

agent-observability CLAUDE.md is an instructions file for Claude Code from nexus-labs-automation/agent-observability. It costs 1,309 tokens per session, scanned A, original, MIT.

Guidance for observing AI agents by recording what they intended to do, how they used language models and tools, and what happened afterward.

In plain words
What is it for?
Planning instrumentation, tracing model calls and tool use, observing multi-agent workflows, tracking tokens and costs, and setting evaluation metrics.
Why use it?
It helps teams find missing records, understand failures, track human intervention, and measure usage and cost across agent workflows.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is nexus-labs-automation/agent-observability's own configuration. It tells Claude Code how to work on agent-observability itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-observability configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nexus-labs-automation/agent-observability. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nexus-labs-automation/agent-observability/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/nexus-labs-automation/agent-observability

Made for: Claude Code.

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 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nexus-labs-automation/agent-observability/claude-md/github.svg)](https://agentmods.dev/instructions/nexus-labs-automation/agent-observability/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nexus-labs-automation/agent-observability/claude-md"><img src="https://agentmods.dev/badge/instructions/nexus-labs-automation/agent-observability/claude-md/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.

agentmods 80×15 button for agent-observability CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nexus-labs-automation/agent-observability/claude-md"><img src="https://agentmods.dev/badge/instructions/nexus-labs-automation/agent-observability/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,309 This file is loaded in full into every session.
When invoked 1,309 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01309 $0.01309
Opus 5 $0.00655 $0.00655
Sonnet 5 $0.00262 $0.00262
Haiku 4.5 $0.00131 $0.00131

Measured 10d ago against content hash f61a65c0dde9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-observability CLAUDE.md 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 10d 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.

CLAUDE.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Observability Plugin

Expert guidance for instrumenting AI agents in production. This plugin teaches best practices for observing multi-agent systems, LLM calls, tool executions, and agent workflows.

When to Use This Plugin

  • Setting up observability for new agent systems
  • Adding tracing to existing LangChain/LangGraph applications
  • Instrumenting Claude Agent SDK or OpenAI Agents
  • Auditing agent telemetry for gaps and anti-patterns
  • Tracking token usage and costs across agents
  • Implementing evaluation and quality metrics

Core Philosophy

Agent-Focused Observability answers three questions for every agent action:

  1. Intent: What was the agent trying to accomplish?
  2. Execution: How did the agent attempt to achieve it (LLM calls, tool use, reasoning)?
  3. Outcome: Did it succeed, fail, or require human intervention?

Skill Routing

Topic Skill Priority
What to measure instrumentation-planning P1
LLM call tracing llm-call-tracing P1
Tool execution tool-call-tracking P1
Multi-agent workflows multi-agent-coordination P1
Token/cost tracking token-cost-tracking P1
Prompt A/B testing prompt-versioning P1
Safety & guardrails guardrails-safety P1
Agent decision tracing decision-tracing P1
Production eval strategy production-eval-strategy P1
RAG/memory memory-rag-instrumentation P2
Human-in-the-loop human-in-the-loop P2
Errors and retries error-retry-tracking P2
Quality metrics evaluation-quality P2
Sessions/conversations session-conversation-tracking P2

Commands

Command Purpose
/instrument Generate instrumentation plan for agent system
/audit Scan existing telemetry and identify gaps

Reference Loading (Context Budget)

All files <9KB - safe to load individually.

Condition Load Size
Planning instrumentation references/methodology/*.md 5-8KB
Framework detected references/frameworks/{framework}.md 6-8KB
Vendor specified references/vendors/{vendor}.md 7-8KB
Reporting issues references/anti-patterns/*.md 5-9KB
Generating code templates/*.py 3-5KB

Read the full file on GitHub · 129 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. 10d ago First seen · 129 lines · 1,309 tokens per session scan A f61a65c0dde9

Subscribe to this mod's changes

agent-observability CLAUDE.md is an instructions file published in the GitHub repository nexus-labs-automation/agent-observability (7 stars, last pushed 8mo ago), licensed MIT. It adds 1,309 tokens to every session, about $0.0065 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens