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 thermiteau/maverick --skill do-maverick-alignmentgit clone --depth 1 https://github.com/thermiteau/maverickWrote 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/thermiteau/maverick/do-maverick-alignment)<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>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 | $0.00062 | $0.03887 |
| Opus 5 | $0.00031 | $0.01944 |
| Sonnet 5 | $0.00012 | $0.00777 |
| Haiku 4.5 | $0.00006 | $0.00389 |
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.
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-> TypeScriptpyproject.tomlorrequirements.txt-> Pythonbuild.gradle.kts-> KotlinDockerfile-> 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.
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.
- 8d ago First seen · 416 lines · 62 tokens per session scan A 81d71ab2287a
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…