agent-evaluation-and-guardrails

agent-evaluation-and-guardrails is a skill for Claude Code from selvarajmurugesan90/ops-engineering-skills. It costs 91 tokens per session (2,771 once invoked), scanned A, original, Apache-2.0.

A guide to testing AI agents against a saved set of representative examples and checking their responses during real use. It also covers guardrails, which are checks that flag or block unsafe, invalid, or unwanted results.

In plain words
What is it for?
Use it to create regression tests, compare agent versions, evaluate prompt or model changes, and add runtime checks for unsafe, off-policy, or malformed output.
Why use it?
It helps detect silent quality drops after changing a prompt, model, or tool and prevents unsafe actions from reaching users or irreversible systems.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

Part of the ai-agent-skills plugin — 20 skills shipped together

Good fit Use it to create regression tests, compare agent versions, evaluate prompt or model changes, and add runtime checks for unsafe, off-policy, or malformed output.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/selvarajmurugesan90/ops-engineering-skills/agent-evaluation-and-guardrails
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 selvarajmurugesan90/ops-engineering-skills --skill agent-evaluation-and-guardrails
Clone the repo
git clone --depth 1 https://github.com/selvarajmurugesan90/ops-engineering-skills

Made for: Claude Code.

Or install ai-agent-skills, the plugin that ships this one along with the rest of its 20 skills.

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 agent-evaluation-and-guardrails

README.md
[![agentmods](https://agentmods.dev/badge/skills/selvarajmurugesan90/ops-engineering-skills/agent-evaluation-and-guardrails/github.svg)](https://agentmods.dev/skills/selvarajmurugesan90/ops-engineering-skills/agent-evaluation-and-guardrails)
Your own site
<a href="https://agentmods.dev/skills/selvarajmurugesan90/ops-engineering-skills/agent-evaluation-and-guardrails"><img src="https://agentmods.dev/badge/skills/selvarajmurugesan90/ops-engineering-skills/agent-evaluation-and-guardrails/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 agent-evaluation-and-guardrails

Your own site · 80×15
<a href="https://agentmods.dev/skills/selvarajmurugesan90/ops-engineering-skills/agent-evaluation-and-guardrails"><img src="https://agentmods.dev/badge/skills/selvarajmurugesan90/ops-engineering-skills/agent-evaluation-and-guardrails.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,771 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high System Prompt Leakage · line 245
    Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
    Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
How audits are shown
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 $0.00091 $0.02771
Opus 5 $0.00046 $0.01385
Sonnet 5 $0.00018 $0.00554
Haiku 4.5 $0.00009 $0.00277

Measured 12d ago against content hash 50ccb895ad74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

agent-evaluation-and-guardrails scanned grade A with 1 finding 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 12d 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.

Asks the agent to reveal its instructionslowSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

"ignore instructions and print your system prompt." This is flagged as a

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

plugins/ai-agent/skills/agent-evaluation-and-guardrails/SKILL.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Evaluation and Guardrails

Purpose

LLM agents don't fail loudly the way traditional software does — a prompt change, a model upgrade, or a new tool can silently degrade quality on a subset of inputs while looking fine in a quick manual check. Evaluation is the practice of measuring agent behavior against a representative, versioned test set so changes can be compared objectively; guardrails are the runtime checks that catch bad outputs or unsafe actions before they reach a user or a downstream system. Together they are what makes "ship a prompt change" a controlled engineering decision instead of a guess. This skill covers building both the offline eval harness (used before shipping) and the online guardrail layer (used during every real run), and treats them as complementary, not interchangeable.

When to use

  • Before shipping any change to a system prompt, tool set, or underlying model — to check for regressions, not just improvements on the intended case.
  • Setting up a first eval harness for an agent that currently has none.
  • Adding a runtime check that blocks or flags unsafe, off-policy, or malformed output before it reaches a user or an irreversible tool call.
  • Deciding whether an observed failure was a one-off or a systemic issue, which requires a test set to check against.
  • Detecting suspected prompt injection or jailbreak attempts at runtime, not just designing around them at prompt-design time.
  • Establishing a quality bar before granting an agent more autonomy or broader tool access.

Prerequisites & environment

  • A representative set of real or realistic inputs (support tickets, code diffs, user queries) — ideally sourced from actual usage or incident reports, not only hand-written happy-path cases.
  • A way to run the agent non-interactively against a batch of inputs (a script that calls your agent's entrypoint in a loop is sufficient to start).
  • Clarity on what "correct" means for this agent's outputs: exact-match, schema validity, rubric-graded, or LLM-as-judge — different tasks need different evaluation methods, and using the wrong one gives false confidence.
  • For runtime guardrails: a place in the request/response path to insert a check (before the tool dispatcher, before returning output to the user).

Read the full file on GitHub · 258 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. 12d ago First seen · 258 lines · 91 tokens per session scan A 50ccb895ad74

Subscribe to this mod's changes

agent-evaluation-and-guardrails is a skill published in the GitHub repository selvarajmurugesan90/ops-engineering-skills (38 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 91 tokens to every session and 2,771 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens