agentmods.dev

gs:maintainer-auditor

gs:maintainer-auditor is a skill for Claude Code, Codex from thanh-abaii/gstack-windows-port. It costs 96 tokens per session (962 once invoked), scanned B, original, MIT.

An automated review of active project files for Unix-only code, fixed Unix file paths, and exposed secrets, with a Windows 11 release checklist.

In plain words
What is it for?
Use it to audit a pull request or project for Windows compatibility, hardcoded paths, unusual line endings, and leaked API keys.
Why use it?
It helps find portability and security problems before a project is released or reviewed. It also records the findings in a report.

Skill for Claude CodeCodex

Written for Claude Code and Codex: allowed-tools in frontmatter, but also agents/openai.yaml present. Also seen: names the AskUserQuestion tool; mentions Codex; built for gstack.

not rated 35repo +1 3mo ago B scan 96 tokens original MIT

Good fit Use it to audit a pull request or project for Windows compatibility, hardcoded paths, unusual line endings, and leaked API keys.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thanh-abaii/gstack-windows-port/gstack-maintainer-auditor
View source ↗ thanh-abaii/gstack-windows-port
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 thanh-abaii/gstack-windows-port --skill gstack-maintainer-auditor
Clone the repo
git clone --depth 1 https://github.com/thanh-abaii/gstack-windows-port

Made for: Claude Code, Codex.

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 gs:maintainer-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/thanh-abaii/gstack-windows-port/gstack-maintainer-auditor.svg)](https://agentmods.dev/skills/thanh-abaii/gstack-windows-port/gstack-maintainer-auditor)
Your own site
<a href="https://agentmods.dev/skills/thanh-abaii/gstack-windows-port/gstack-maintainer-auditor"><img src="https://agentmods.dev/badge/skills/thanh-abaii/gstack-windows-port/gstack-maintainer-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 962 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00096 $0.00962
Opus 5 $0.00048 $0.00481
Sonnet 5 $0.00019 $0.00192
Haiku 4.5 $0.00010 $0.00096

Measured 8d ago against content hash 5631806ad22f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

gs:maintainer-auditor scanned grade B 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (maintainer_auditor.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Tự động đề xuất đoạn mã sửa đổi** bằng PowerShell thuần túy Windows (Ví dụ: thay thế `rm -rf` bằng `Remove-Item -Recurse -Force`, `mkdir -p` bằng `New-Item -ItemType Directory -Force`).

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

skills/gstack-maintainer-auditor/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Preamble (run first)

python "bin/gstack-boot.py" --skill maintainer-auditor | iex

System Intent & Workflow Hướng dẫn Agent

Bạn là Maintainer Auditor Agent, một chuyên gia bảo mật và tương thích Windows chuyên nghiệp phụ trách kiểm toán dự án nguồn mở nhằm hỗ trợ nộp đơn OpenAI Codex for Open Source. Khi skill này được kích hoạt, bạn PHẢI thực hiện tuần tự 4 bước nghiêm ngặt sau:

🚀 BƯỚC 1: Thực thi kiểm toán tĩnh (Static Analysis Scan)

Bạn hãy chạy script Python kiểm toán bằng cách thực hiện lệnh sau trong PowerShell:

python skills/gstack-maintainer-auditor/maintainer_auditor.py

Lệnh này sẽ tự động phân tích tĩnh toàn bộ mã nguồn của workspace (bỏ qua các tệp trong .gitignore), quét sạch các lỗi tương thích hệ điều hành Windows, các đường dẫn nhị phân Unix, các Line Endings bất chuẩn và lộ lọt khoá bí mật API (OpenAI/Google). Kết quả báo cáo định dạng Markdown sẽ được ghi tại reports/maintainer_audit_report.md.

📂 BƯỚC 2: Phân tích & Trình bày kết quả Quét tương thích

  1. Hãy đọc tệp báo cáo vừa tạo tại reports/maintainer_audit_report.md bằng công cụ đọc file.
  2. Trình bày lại tóm tắt báo cáo cho người dùng dưới dạng một bảng thống kê trực quan.
  3. Nếu phát hiện thấy bất kỳ lỗi tương thích nào (Bashisms hoặc Unix Paths):
    • Chỉ ra chính xác dòng code và tệp tin bị vi phạm.
    • Tự động đề xuất đoạn mã sửa đổi bằng PowerShell thuần túy Windows (Ví dụ: thay thế rm -rf bằng Remove-Item -Recurse -Force, mkdir -p bằng New-Item -ItemType Directory -Force).

🔍 BƯỚC 3: Đánh giá Pull Request & Kiến trúc Mã nguồn bằng LLM

Sử dụng năng lực suy luận của bạn để thực hiện một buổi đánh giá mã nguồn (PR Review) phong cách kỹ sư cao cấp:

  1. Logic & Chức năng: Đánh giá tính lũy đẳng (idempotent), kiểm thử điều kiện biên và cấu trúc kiểm soát lỗi.
  2. Tuân thủ Windows Native: Đảm bảo mã nguồn hoàn toàn không sử dụng các giả định Unix/Linux.
  3. Độ phủ Kiểm thử (Test Coverage): Kiểm tra xem các thay đổi đã có kịch bản chạy thử tương ứng chưa.
  4. An ninh nguồn mở (Codex Security): Đánh giá rủi ro lộ bí mật hoặc quyền truy cập hệ thống.

Read the full file on GitHub · 74 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 74 lines · 96 tokens per session scan B 5631806ad22f

Subscribe to this mod's changes

gs:maintainer-auditor is a skill published in the GitHub repository thanh-abaii/gstack-windows-port (35 stars, last pushed 3mo ago), licensed MIT. It adds 96 tokens to every session and 962 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code reviewSecurity
Related

Other skills, from other repositories

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

rework-rate

Measure and interpret PR rework rate — the emerging 5th DORA metric.

bradygaster/squad · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

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"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

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…

LeoYeAI/openclaw-master-skills · 115 tokens