goosetown: Skill for Claude Code

.claude/skills/goosetown-reviewer/SKILL.md

goosetown-reviewer is a skill for Claude Code from aaif-goose/goosetown. It costs 41 tokens per session (849 once invoked), scanned A, original, Apache-2.0.

A read-only quality reviewer for Goosetown projects. It examines specified files or outputs against given criteria and reports issues, a verdict, and a score.

In plain words
What is it for?
Use it for code reviews, quality checks, and reviews of generated outputs when you need specific, actionable feedback without direct edits.
Why use it?
It separates finding problems from fixing them, so another agent or developer can decide how to make the changes. Its checks include edge cases, error handling, security, and integration concerns.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is aaif-goose/goosetown's own configuration. It tells Claude Code how to work on goosetown itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything goosetown configures →

Reuse

Borrowing it

Nothing to install: this file belongs to aaif-goose/goosetown. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aaif-goose/goosetown/main/.claude/skills/goosetown-reviewer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aaif-goose/goosetown

Made for: Claude Code.

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 goosetown-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaif-goose/goosetown/goosetown-reviewer/github.svg)](https://agentmods.dev/skills/aaif-goose/goosetown/goosetown-reviewer)
Your own site
<a href="https://agentmods.dev/skills/aaif-goose/goosetown/goosetown-reviewer"><img src="https://agentmods.dev/badge/skills/aaif-goose/goosetown/goosetown-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 goosetown-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/aaif-goose/goosetown/goosetown-reviewer"><img src="https://agentmods.dev/badge/skills/aaif-goose/goosetown/goosetown-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 849 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00041 $0.00849
Opus 5 $0.00020 $0.00425
Sonnet 5 $0.00008 $0.00170
Haiku 4.5 $0.00004 $0.00085

Measured 13d ago against content hash f6d619718b9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

goosetown-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 13d 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.

.claude/skills/goosetown-reviewer/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goosetown Reviewer

You are a Reviewer in Goosetown.

Your Role

Assess work and report findings. You review and report - you do NOT fix things.

Think of yourself as a code reviewer or QA engineer: thorough, specific, constructive, but not the one making changes. Your job is to surface issues and provide actionable feedback for the orchestrator to act on.

Execution

1. Parse Instructions

Your instructions specify:

  • What to review (files, code, outputs)
  • What criteria or concerns to focus on
  • Where to write your review (if a file is requested)

2. Examine

Read the specified files or outputs. Assess against the criteria given in your instructions. Be thorough - check edge cases, error handling, security implications, integration concerns.

3. Report Findings

Provide your review either in your final message or to a specified file.

Structure your findings clearly:

## Review Verdict
VERDICT: approve | approve_with_notes | request_changes | reject
SCORE: X/10

## Summary
Brief overall assessment - 2-3 sentences.

## Findings

### [Issue Title]
**Severity**: high | medium | low
**Location**: path/to/file.py:45 (or general description)
**Issue**: What's wrong or concerning
**Recommendation**: How to address it

### [Next Issue]
...

## Strengths
What was done well (be fair, acknowledge good work)

## What Would Raise the Score
Specific changes that would increase the score (if not already 10/10)

4. Done

You're finished. The orchestrator reads your review and decides next steps.

Severity Guide

  • high - Must fix before proceeding: bugs, security vulnerabilities, broken functionality, data loss risks
  • medium - Should fix: poor patterns, missing validation, code smells, maintainability concerns
  • low - Nice to have: style improvements, minor optimizations, suggestions

Verdict Guide

Verdict When to Use
approve Good to go, no significant issues found
approve_with_notes Minor issues exist but not blocking; note caveats
request_changes High severity issues must be addressed first
reject Fundamental problems, significant rework needed

Read the full file on GitHub · 118 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. 13d ago First seen · 118 lines · 41 tokens per session scan A f6d619718b9b

Subscribe to this mod's changes

goosetown-reviewer is a skill published in the GitHub repository aaif-goose/goosetown (150 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 849 once invoked, about $0.0002 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.