Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Agent metrics instrumentation v1.0.0

Use this resource to instrument AI model calls to track their metrics in LaunchDarkly

New

  • 344 downloads
  • 236 likes
  • 194 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install agent-metrics-instrumentation

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent reviews your existing provider calls and picks the simplest tier that captures duration, tokens and success or error. It implements that tier from the matching provider guide, without rewriting your call.

Mostly picked by

Updated November 2, 2026

Card for the “Agent metrics instrumentation” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: four-tier ladder and instrumentation method
  • references/: guides per provider (Anthropic, OpenAI, Gemini, Bedrock, LangChain, Strands, streaming)

Good fit for

  • Your code calls an AI model and you want to track its cost and errors
  • You stream responses and want to measure time to first token

Not for

    Tags

    • metrics
    • AI agents
    • instrumentation
    • tokens

    About

    You say

    “Instrument my OpenAI call to track duration, tokens and errors in LaunchDarkly.”

    Card for the “Agent metrics instrumentation” skill

    Skill published by launchdarkly under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to instrument AI model calls to track their metrics in LaunchDarkly
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE0.6 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/anthropic-tracking.md6.6 KB
    • references/bedrock-tracking.md5.6 KB
    • references/gemini-tracking.md10.4 KB
    • references/langchain-tracking.md17.8 KB
    • references/metrics-api.md3.3 KB
    • references/openai-tracking.md6.3 KB
    • references/strands-tracking.md5 KB
    • references/streaming-tracking.md7.1 KB
    • SKILL.md12.6 KB

    Origin and licence

    Listed unmodified

    Author
    launchdarkly
    Source
    github.com/launchdarkly/ai-tooling/tree/c26f86ad64ade56b205afea30a40f3a25f51983f/skills/agentcontrol/built-in-metrics
    Licence
    Apache-2.0

    Notice

    « built-in-metrics » (launchdarkly, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.