What is online-evals?

A system for having one AI configuration judge the responses produced by another. These judges return structured quality scores, such as an accuracy score from 0.0 to 1.0.

Use it to create or attach judges, choose how often they review traffic, and monitor scores for response quality.

It removes the need to review every response by hand and makes sampled, ongoing quality checks possible. It requires an existing configuration with alternatives and LaunchDarkly access.

online-evals — Skill for Claude Code and Codex by Bilal140202

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.

Any agent

npx skills add Bilal140202/the-lord-of-the-skills --skill agentcontrol-online-evals

Clone the repo

git clone --depth 1 https://github.com/Bilal140202/the-lord-of-the-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bilal140202/the-lord-of-the-skills/agentcontrol-online-evals/github.svg)](https://agentmods.dev/skills/bilal140202/the-lord-of-the-skills/agentcontrol-online-evals)

Your own site

<a href="https://agentmods.dev/skills/bilal140202/the-lord-of-the-skills/agentcontrol-online-evals"><img src="https://agentmods.dev/badge/skills/bilal140202/the-lord-of-the-skills/agentcontrol-online-evals/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bilal140202/the-lord-of-the-skills/agentcontrol-online-evals"><img src="https://agentmods.dev/badge/skills/bilal140202/the-lord-of-the-skills/agentcontrol-online-evals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,853 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.00032	$0.03853
Opus 5	$0.00016	$0.01927
Sonnet 5	$0.00006	$0.00771
Haiku 4.5	$0.00003	$0.00385

Measured 6d ago against content hash 4c83e0e91c6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

online-evals scanned grade B with 2 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 6d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

2. **Check MCP config** - Claude: `~/.claude/config.json` -> `mcpServers.launchdarkly.env.LAUNCHDARKLY_API_KEY`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST "https://app.launchdarkly.com/api/v2/projects/{projectKey}/ai-configs" \

skills/gondor/claude-code/LaunchDarkly__agent-skills/agentcontrol-online-evals-SKILL.md · 456 lines

How it starts

The opening of the file, as written. The whole thing — 456 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Config Online Evaluations

Attach judges to config variations for automatic quality scoring using LLM-as-a-judge methodology. Judges evaluate responses and return scores between 0.0 and 1.0.

Prerequisites

LaunchDarkly account with AgentControl enabled
API access token with write permissions
Existing config with variations (use configs-create skill)
For automatic metric recording and the consolidated judge-result API: Python AI SDK v0.20.0+ or Node.js AI SDK v0.20.0+

API Key Detection

Check environment variables - LAUNCHDARKLY_API_KEY, LAUNCHDARKLY_API_TOKEN, LD_API_KEY
Check MCP config - Claude: ~/.claude/config.json -> mcpServers.launchdarkly.env.LAUNCHDARKLY_API_KEY
Prompt user - Only if detection fails

Core Concepts

What Are Judges?

Judges are specialized configs in judge mode that evaluate responses from other configs. They use an LLM to score outputs and return structured results:

{
  "score": 0.85,
  "reasoning": "Answered correctly with one minor omission"
}

Built-in Judges

LaunchDarkly provides three pre-configured judges:

Judge	Metric Key	Measures
Accuracy	`$ld:ai:judge:accuracy`	How correct and grounded the response is
Relevance	`$ld:ai:judge:relevance`	How well it addresses the user request
Toxicity	`$ld:ai:judge:toxicity`	Harmful or unsafe phrasing (lower = safer)

Completion Mode Only

Judges can only be attached to completion mode configs in the UI. For agent mode or custom pipelines, use programmatic evaluation via the SDK.

Restrictions

Cannot attach judges to judges (no recursion)
Cannot attach multiple judges with the same metric key to a single variation
Cannot view/edit model parameters or tools on judge variations

Workflow

Step 1: Create Custom Judges (Optional)

For domain-specific evaluation, create judge configs:

# Create judge config
curl -X POST "https://app.launchdarkly.com/api/v2/projects/{projectKey}/ai-configs" \
  -H "Authorization: {api_token}" \
  -H "Content-Type: application/json" \
  -H "LD-API-Version: beta" \
  -d '{
    "key": "security-judge",
    "name": "Security Judge",
    "mode": "judge",
    "evaluationMetricKey": "security",
    "isInverted": false
  }'

Read the full file on GitHub · 456 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.

6d ago First seen · 456 lines · 32 tokens per session scan B 4c83e0e91c6f

Subscribe to this mod's changes

online-evals is a skill published in the GitHub repository Bilal140202/the-lord-of-the-skills (4 stars, last pushed 6d ago), licensed MIT. It adds 32 tokens to every session and 3,853 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.

Analytics and metrics Data and AI agentic-ai ai-agents aider awesome-list cline

agents-meet-rl

Troubleshooter for agentic-RL training, evaluation, and experiment design on LLM agents (single or multi-agent, multi-turn, tool-augmented). Routes a user's symptom to fixes anchored in the corpus. TRIGGER when: user is training, evaluating, or designing experiments for an RL-trained LLM agent; symptoms like reward…

thinkwee/AgentsMeetRL · 220 tokens

hunt-llm-ai

Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use, ASCII smuggling, agentic AI security framework (ASI01-ASI10). Patterns: direct prompt injection in user input (bypass system prompt with 'ignore previous instructions'), indirect injection via documents/web pages the model…

adriannoes/awesome-agentic-ai · 226 tokens

online-evals