benchmark

benchmark is a command for Claude Code from HermeticOrmus/LibreSecOps-Claude-Code. It costs 23 tokens per session (737 once invoked), scanned A, original, MIT.

A compliance assessment command that checks a system's settings against CIS Benchmarks, which are published security checklists for platforms such as Ubuntu, Docker, Kubernetes, AWS, and Nginx.

In plain words
What is it for?
Use it to assess a platform, compare results with an earlier report, or check selected benchmark sections at Level 1 or Level 2.
Why use it?
It replaces a manual comparison of configuration settings with a structured pass/fail report. It also helps identify configuration drift and prepare evidence for security audits.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the security-hardening plugin — 1 skill, 2 commands, 2 agents shipped together

Good fit Use it to assess a platform, compare results with an earlier report, or check selected benchmark sections at Level 1 or Level 2.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/hermeticormus/libresecops-claude-code/benchmark
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.

Clone the repo
git clone --depth 1 https://github.com/HermeticOrmus/LibreSecOps-Claude-Code

Made for: Claude Code.

Or install security-hardening, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 2 agents.

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 benchmark

README.md
[![agentmods](https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/benchmark/github.svg)](https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/benchmark)
Your own site
<a href="https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/benchmark"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/benchmark/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 benchmark

Your own site · 80×15
<a href="https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/benchmark"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/benchmark.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 737 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.00737
Opus 5.5 $0.00009 $0.00295
Sonnet 5.5 $0.00005 $0.00147
Haiku 4.5 $0.00002 $0.00074

Measured 1mo ago against content hash 43c65c52efe3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

benchmark 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 1mo 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.

plugins/security-hardening/commands/benchmark.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/benchmark

Assess configuration against CIS Benchmark requirements and produce a compliance report.

Trigger

Use this command when:

  • Conducting a CIS Benchmark compliance assessment
  • Preparing for a security audit that references CIS controls
  • Validating that hardening changes were applied correctly
  • Establishing a baseline compliance score for a system
  • Monitoring configuration drift from hardened state

Input

Required:

  • Target: Platform to assess (e.g., ubuntu-22.04, docker, kubernetes, aws, nginx)

Optional:

  • Profile: level-1 or level-2 (defaults to level-1)
  • Configuration: Path to configuration files for static analysis
  • Previous assessment: Path to previous report for delta comparison
  • Sections: Specific benchmark sections to assess (comma-separated)

Process

Step 1: Benchmark Selection

  1. Match target platform to the correct CIS Benchmark document and version
  2. Apply the selected profile level (Level 1 or Level 2)
  3. Filter to specified sections if provided

Step 2: Control Assessment

For each applicable control in the benchmark:

  1. Read the requirement: What the CIS Benchmark specifies
  2. Check current state: Examine configuration files, system settings, or cloud configuration
  3. Assess compliance: PASS (meets requirement), FAIL (does not meet), N/A (not applicable to this environment)
  4. Document evidence: The specific configuration value or command output that supports the assessment
  5. Provide remediation: For FAIL findings, specific steps to achieve compliance

Step 3: Scoring

Calculate compliance percentage:

  • Only scored controls count toward the percentage
  • Not Applicable controls are excluded from the total
  • Compliance % = Passed / (Passed + Failed) * 100

Step 4: Gap Analysis

For failed controls:

  1. Group by severity (critical gaps vs minor gaps)
  2. Estimate remediation effort for each
  3. Identify dependencies between controls
  4. Produce a prioritized remediation plan

Read the full file on GitHub · 102 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. 1mo ago Changed · +5 lines · +23 tokens per session 43c65c52efe3
  2. 2mo ago First seen · 97 lines · 0 tokens per session scan A 07d368444a79

Subscribe to this mod's changes

benchmark is a command published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 737 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.

Related

benchmark compared with commands from other repositories

benchmark next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
benchmarkHermeticOrmus/LibreSecOps-Claude-CodeCommand41mo agoMITA23Claude Code
build-agentis-bo/fullstack-forge-skillCommand2yesterdayApache-2.0A11Claude Code
build-mcpis-bo/fullstack-forge-skillCommand2yesterdayApache-2.0A12Claude Code
checklistgithub/spec-kitCommand148kyesterdayMITA13Claude Code
clarifygithub/spec-kitCommand148kyesterdayMITA27Claude Code
specifygithub/spec-kitCommand148kyesterdayMITA13Claude Code
analyzegithub/spec-kitCommand148kyesterdayMITA26Claude Code