do-maverick-alignment

do-maverick-alignment is a skill for Claude Code from thermiteau/maverick. It costs 62 tokens per session (3,887 once invoked), scanned A, original, Apache-2.0.

A codebase audit that checks a project against Maverick’s recommended engineering practices and saves a findings report in `docs/maverick-audit.md`.

In plain words
What is it for?
Run it when onboarding an existing project or reviewing one on demand. It detects the project’s technology stack, checks each category, scores findings, writes the report, and summarises the results.
Why use it?
It gives a structured view of gaps in areas such as testing, documentation, security, dependencies, CI/CD, and observability, instead of relying on an informal review.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents.

Part of the maverick plugin — 41 skills, 5 agents, 5 hooks shipped together

Good fit Run it when onboarding an existing project or reviewing one on demand. It detects the project’s technology stack, checks each category, scores findings, writes the report, and summarises the results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thermiteau/maverick/do-maverick-alignment
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 thermiteau/maverick --skill do-maverick-alignment
Clone the repo
git clone --depth 1 https://github.com/thermiteau/maverick

Made for: Claude Code.

Or install maverick, the plugin that ships this one along with the rest of its 41 skills, 5 agents, 5 hooks.

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 do-maverick-alignment

README.md
[![agentmods](https://agentmods.dev/badge/skills/thermiteau/maverick/do-maverick-alignment.svg)](https://agentmods.dev/skills/thermiteau/maverick/do-maverick-alignment)
Your own site
<a href="https://agentmods.dev/skills/thermiteau/maverick/do-maverick-alignment"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/do-maverick-alignment.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,887 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 $0.00062 $0.03887
Opus 5 $0.00031 $0.01944
Sonnet 5 $0.00012 $0.00777
Haiku 4.5 $0.00006 $0.00389

Measured 8d ago against content hash 81d71ab2287a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

do-maverick-alignment 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 8d 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.

skills/do-maverick-alignment/SKILL.md · 416 lines

How it starts

The opening of the file, as written. The whole thing — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Audit

Analyze the current project's codebase against Maverick standard practices and write a findings report to docs/maverick-audit.md.

Preflight (mandatory)

Run this first. If it exits non-zero, halt and report the stderr output to the user verbatim. Do not proceed.

uv run maverick preflight do-maverick-alignment

The check verifies the project is initialised and uv is on PATH.

When to Run

  • User invokes /maverick:do-maverick-alignment
  • May also be triggered automatically by the Maverick plugin when no .maverick/ directory exists in the project root (first session in an uninitialised project)

Process

digraph audit {
    "Detect project stack" [shape=box];
    "Check each category" [shape=box];
    "Score findings" [shape=box];
    "Write report" [shape=box];
    "Summarise to user" [shape=box];

    "Detect project stack" -> "Check each category";
    "Check each category" -> "Score findings";
    "Score findings" -> "Write report";
    "Write report" -> "Summarise to user";
}

Step 1: Detect project stack

Identify the project type by checking for key files:

  • package.json -> Node.js (check dependencies for react, fastify, etc.)
  • tsconfig.json -> TypeScript
  • pyproject.toml or requirements.txt -> Python
  • build.gradle.kts -> Kotlin
  • Dockerfile -> Docker

Record the detected stack for the report header.

Monorepos: If workspaces is defined in package.json, or pnpm-workspace.yaml / nx.json / turbo.json exists, treat the root config as the primary audit target. Note per-package gaps in the Details section but do not produce a separate report per package.

Step 2: Check each category

Run the checks below in order. For each category, determine a status:

  • PASS -- meets Maverick standards
  • WARN -- partially meets standards, improvement needed
  • FAIL -- does not meet standards

Record the evidence (file paths, dependency names, snippets) for each finding.

Read the full file on GitHub · 416 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. 8d ago First seen · 416 lines · 62 tokens per session scan A 81d71ab2287a

Subscribe to this mod's changes

do-maverick-alignment is a skill published in the GitHub repository thermiteau/maverick (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 3,887 once invoked, about $0.0003 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 2026-08-30.