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.
git clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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.
[](https://agentmods.dev/commands/jnpiyush/agentx/evaluation)<a href="https://agentmods.dev/commands/jnpiyush/agentx/evaluation"><img src="https://agentmods.dev/badge/commands/jnpiyush/agentx/evaluation/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.
<a href="https://agentmods.dev/commands/jnpiyush/agentx/evaluation"><img src="https://agentmods.dev/badge/commands/jnpiyush/agentx/evaluation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00019 | $0.00715 |
| Opus 5 | $0.00010 | $0.00358 |
| Sonnet 5 | $0.00004 | $0.00143 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
AI Evaluation Setup 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Evaluation Setup Prompt
Context
You are adding evaluation for the AI agent/application in issue {{issue_number}}.
Before writing code, review:
- AI Agent Development Skill (Evaluation section):
.github/skills/ai-systems/ai-agent-development/SKILL.md - Existing agent code to understand inputs/outputs
Instructions
1. Create Test Dataset
Build a representative dataset:
- Minimum 10 queries covering happy path, edge cases, and adversarial inputs
- Format: JSONL file with
query,context(if RAG), andground_truth(if available) - Store at:
tests/eval/dataset.jsonl
{"query": "What is the refund policy?", "ground_truth": "30-day money back guarantee", "context": "..."}
{"query": "How do I cancel?", "ground_truth": "Go to Settings > Subscription > Cancel", "context": "..."}
2. Select Evaluators
Choose from built-in evaluators based on your scenario:
| Evaluator | Use when |
|---|---|
RelevanceEvaluator |
Checking if response addresses the query |
CoherenceEvaluator |
Checking response readability and flow |
GroundednessEvaluator |
RAG - checking if response is grounded in context |
SimilarityEvaluator |
Comparing response to ground truth |
FluencyEvaluator |
Checking language quality |
Add custom evaluators for domain-specific checks (format validation, keyword presence, etc.).
3. Write Evaluation Script
# tests/eval/run_eval.py
import asyncio
from azure.ai.evaluation import evaluate, RelevanceEvaluator, CoherenceEvaluator
results = evaluate(
data="tests/eval/dataset.jsonl",
evaluators={
"relevance": RelevanceEvaluator(model_config),
"coherence": CoherenceEvaluator(model_config),
},
evaluator_config={
"default": {
"query": "${data.query}",
"response": "${target.response}",
}
},
)
4. Define Pass Criteria
Set minimum thresholds:
- Relevance 4.0 / 5.0
- Coherence 4.0 / 5.0
- Custom metrics: define per project
5. Integrate with CI (Optional)
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.
- 2d ago First seen · 103 lines · 19 tokens per session scan A 01845e266241
AI Evaluation Setup is a command published in the GitHub repository jnPiyush/AgentX (15 stars, last pushed yesterday), licensed Apache-2.0. It adds 19 tokens to every session and 715 once invoked, about $0.0001 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 2026-09-06.
Other commands, from other repositories
rag-eval-init
Scaffold a RAG evaluation setup — golden set template, eval runner, metrics, CI gate.
dark-factory-test-rag-response
Comprehensive test scenario 3 - verify RAG pipeline grounds answers in ingested video and surfaces citations.
proofrag
Evaluate a RAG/LLM app — generate a golden set, judge it, and produce a scorecard.
CLAUDE_CODE_F143_CHATBOT_ONLY
A task for fixing and strengthening an AI chatbot and FAQ system, adding regulation information retrieval, conversation history, and tests. RAG means retrieving relevant source content before generating an answer.
querying
Query documents from a search index using type-safe filters with support for pagination, sorting, field selection, scoring, and highlighting. Count matching documents efficiently without returning results.
agent
Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.