ansible-reviewer

ansible-reviewer is an agent for Claude Code from basher83/lunar-claude. It costs 614 tokens per session (3,290 once invoked), scanned A, original, MIT.

A command that runs ansible-lint, a checker for common quality and style problems in Ansible code, and explains the results.

In plain words
What is it for?
Use it to check a playbook or the whole Ansible directory for missing names, unsafe command reporting, and module naming problems.
Why use it?
It turns lint findings into prioritized issues and practical suggestions for fixing them.

Agent for Claude Code

Written for Claude Code: $CLAUDE_PROJECT_DIR variable. Also seen: model in frontmatter.

Part of the ansible-workflows plugin — 8 skills, 3 commands, 5 agents shipped together

Good fit Use it to check a playbook or the whole Ansible directory for missing names, unsafe command reporting, and module naming problems.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/basher83/lunar-claude/ansible-reviewer
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/basher83/lunar-claude

Made for: Claude Code.

Or install ansible-workflows, the plugin that ships this one along with the rest of its 8 skills, 3 commands, 5 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 ansible-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/basher83/lunar-claude/ansible-reviewer/github.svg)](https://agentmods.dev/agents/basher83/lunar-claude/ansible-reviewer)
Your own site
<a href="https://agentmods.dev/agents/basher83/lunar-claude/ansible-reviewer"><img src="https://agentmods.dev/badge/agents/basher83/lunar-claude/ansible-reviewer/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 ansible-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/basher83/lunar-claude/ansible-reviewer"><img src="https://agentmods.dev/badge/agents/basher83/lunar-claude/ansible-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 614 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,290 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 $0.00614 $0.03290
Opus 5 $0.00307 $0.01645
Sonnet 5 $0.00123 $0.00658
Haiku 4.5 $0.00061 $0.00329

Measured 9d ago against content hash e289bc2f8ffd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ansible-reviewer 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 9d 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/infrastructure/ansible-workflows/agents/ansible-reviewer.md · 364 lines

How it starts

The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert Ansible code reviewer specializing in infrastructure-as-code best practices for Proxmox VE homelab environments. You perform deep, systematic reviews that go beyond linting to evaluate code quality across multiple dimensions with measurable, structured output.

Your Core Responsibilities

  1. Load comprehensive knowledge by invoking all eight ansible-* skills before analysis
  2. Read and understand all related files including playbooks, roles, variables, templates, and handlers
  3. Analyze code systematically across six quality categories with objective scoring
  4. Generate structured reports with specific findings, line references, and actionable fixes
  5. Provide clear recommendations (APPROVED, APPROVED_WITH_CHANGES, or NEEDS_REWORK)

Review Process

Step 1: Load All Skills

Before analyzing any code, invoke each skill using the Skill tool to ensure comprehensive knowledge:

  • ansible-workflows:ansible-fundamentals
  • ansible-workflows:ansible-playbook-design
  • ansible-workflows:ansible-role-design
  • ansible-workflows:ansible-idempotency
  • ansible-workflows:ansible-secrets
  • ansible-workflows:ansible-error-handling
  • ansible-workflows:ansible-testing
  • ansible-workflows:ansible-proxmox

Load these skills in parallel for efficiency. Each skill provides specific criteria and patterns you must evaluate against.

Step 2: Read All Files

Use Glob to discover and Read to examine all relevant files:

  • Main playbook or role - The primary target of review
  • Included task files - Files referenced via ansible.builtin.include_tasks or ansible.builtin.import_tasks
  • Variable files - defaults/main.yml, vars/main.yml, group_vars, host_vars
  • Templates - Jinja2 templates in templates/ directory
  • Handlers - Handler definitions in handlers/main.yml
  • Meta - Role metadata and dependencies in meta/main.yml

Build a complete picture of the code before analyzing.

Step 3: Analyze by Category

Read the full file on GitHub · 364 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. 9d ago First seen · 364 lines · 614 tokens per session scan A e289bc2f8ffd

Subscribe to this mod's changes

ansible-reviewer is an agent published in the GitHub repository basher83/lunar-claude (23 stars, last pushed today), licensed MIT. It adds 614 tokens to every session and 3,290 once invoked, about $0.0031 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 2026-09-03.

Related

Other agents, from other repositories