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.
npx skills add nexus-labs-automation/agent-observability --skill evaluation-qualitygit clone --depth 1 https://github.com/nexus-labs-automation/agent-observabilityWrote 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/skills/nexus-labs-automation/agent-observability/evaluation-quality)<a href="https://agentmods.dev/skills/nexus-labs-automation/agent-observability/evaluation-quality"><img src="https://agentmods.dev/badge/skills/nexus-labs-automation/agent-observability/evaluation-quality/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/skills/nexus-labs-automation/agent-observability/evaluation-quality"><img src="https://agentmods.dev/badge/skills/nexus-labs-automation/agent-observability/evaluation-quality.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 | $0.00013 | $0.01754 |
| Opus 5 | $0.00006 | $0.00877 |
| Sonnet 5 | $0.00003 | $0.00351 |
| Haiku 4.5 | $0.00001 | $0.00175 |
Grade A, and why
evaluation-quality 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.
How it starts
The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluation and Quality Instrumentation
Instrument evaluation systems to track agent quality and enable continuous improvement.
Core Principle
Quality observability answers:
- How good are agent responses?
- What types of errors occur (hallucination, refusal, etc.)?
- Is quality improving over time?
- What correlates with high/low quality?
- How does human feedback compare to automated evals?
Evaluation Types
Automated Evals
LLM-as-judge or heuristic scoring:
span.set_attribute("eval.type", "automated")
span.set_attribute("eval.method", "llm_judge")
span.set_attribute("eval.model", "claude-3-opus")
span.set_attribute("eval.criteria", "helpfulness")
span.set_attribute("eval.score", 0.85)
span.set_attribute("eval.confidence", 0.92)
Human Feedback
User ratings and corrections:
span.set_attribute("eval.type", "human")
span.set_attribute("eval.feedback_type", "thumbs")
span.set_attribute("eval.score", 1) # 1 = thumbs up, 0 = thumbs down
span.set_attribute("eval.user_id", "user_hash")
span.set_attribute("eval.latency_to_feedback_ms", 45000)
Ground Truth Comparison
Compare to known correct answers:
span.set_attribute("eval.type", "ground_truth")
span.set_attribute("eval.metric", "exact_match")
span.set_attribute("eval.score", 1.0)
span.set_attribute("eval.test_case_id", "test_123")
Quality Dimensions
Correctness
span.set_attribute("quality.factual_accuracy", 0.95)
span.set_attribute("quality.hallucination_detected", False)
span.set_attribute("quality.source_grounded", True)
span.set_attribute("quality.citation_count", 3)
Helpfulness
span.set_attribute("quality.task_completion", 1.0)
span.set_attribute("quality.answered_question", True)
span.set_attribute("quality.actionable", True)
span.set_attribute("quality.conciseness", 0.8)
Safety
span.set_attribute("quality.safety_score", 1.0)
span.set_attribute("quality.refused", False)
span.set_attribute("quality.pii_detected", False)
span.set_attribute("quality.harmful_content", False)
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.
- 10d ago First seen · 276 lines · 13 tokens per session scan A c63a1da85482
evaluation-quality is a skill published in the GitHub repository nexus-labs-automation/agent-observability (7 stars, last pushed 8mo ago), licensed MIT. It adds 13 tokens to every session and 1,754 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…