instrument

instrument is a command for Claude Code from nexus-labs-automation/agent-observability. It costs 8 tokens per session (1,164 once invoked), scanned A, original, MIT.

A command that creates an instrumentation plan for an AI agent codebase. Instrumentation means adding measurements and traces so you can understand how software runs.

In plain words
What is it for?
Use it to analyse a project and plan tracing for supported agent frameworks, observability vendors, important workflows, costs, multi-agent behaviour, and evaluations.
Why use it?
It helps identify the agent framework, existing observability, important code paths, and missing measurements before implementation begins.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the TodoWrite tool.

Part of the agent-observability plugin — 14 skills, 2 commands, 2 agents shipped together

Good fit Use it to analyse a project and plan tracing for supported agent frameworks, observability vendors, important workflows, costs, multi-agent behaviour, and evaluations.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/nexus-labs-automation/agent-observability/instrument
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.

Clone the repo
git clone --depth 1 https://github.com/nexus-labs-automation/agent-observability

Made for: Claude Code.

Or install agent-observability, the plugin that ships this one along with the rest of its 14 skills, 2 commands, 2 agents.

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 instrument

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/nexus-labs-automation/agent-observability/instrument"><img src="https://agentmods.dev/badge/commands/nexus-labs-automation/agent-observability/instrument.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,164 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00008 $0.01164
Opus 5 $0.00004 $0.00582
Sonnet 5 $0.00002 $0.00233
Haiku 4.5 $0.00001 $0.00116

Measured 9d ago against content hash b5700645ca88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

instrument 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 9d 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.

commands/instrument.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/instrument Command

Generate a comprehensive instrumentation plan for AI agent systems.

Arguments

  • framework: langchain|langgraph|claude-agent-sdk|openai-agents|crewai|autogen|semantic-kernel|haystack|auto
  • --vendor: Optional observability vendor (langfuse|langsmith|arize|weave|helicone|braintrust|datadog|opentelemetry)
  • --path: Optional path to analyze (defaults to current directory)

Workflow

Phase 1: Discovery

If framework is auto or not specified:

  1. Search for framework indicators in codebase
  2. Identify primary agent framework
  3. Create initial todo list for tracking progress

Phase 2: Codebase Analysis

Launch codebase-analyzer agent:

Analyze this agent codebase to understand:
1. Agent framework and architecture
2. Existing telemetry/observability
3. Key files and entry points
4. Instrumentation gaps

Phase 3: Clarifying Questions

Ask user about:

  1. Critical Agent Journeys - Which agent workflows are most important?
  2. Cost Sensitivity - How important is token/cost tracking?
  3. Multi-Agent Complexity - Single agent or multi-agent orchestration?
  4. Vendor Preference - Preferred observability platform?
  5. Evaluation Needs - Do you need quality/eval metrics?

Phase 4: Plan Design

Load and apply:

  • skills/instrumentation-planning/SKILL.md
  • references/methodology/agent-observability-tiers.md
  • references/frameworks/{detected-framework}.md (if detected)
  • references/vendors/{specified-vendor}.md (if specified)

Generate tiered implementation plan:

Tier Focus Instrumentation
T0: Foundation Day 1 essentials SDK init, basic spans, error capture
T1: Core Tracing LLM & tools LLM call spans, tool execution spans
T2: Context Attribution Token tracking, cost calculation, user context
T3: Multi-Agent Coordination Parent-child spans, handoffs, delegation
T4: Evaluation Quality Evals, feedback loops, quality metrics

Read the full file on GitHub · 175 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. 9d ago First seen · 175 lines · 8 tokens per session scan A b5700645ca88

Subscribe to this mod's changes

instrument is a command published in the GitHub repository nexus-labs-automation/agent-observability (7 stars, last pushed 8mo ago), licensed MIT. It adds 8 tokens to every session and 1,164 once invoked, about $0.0000 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.