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 ArabelaTso/Skills-4-SE --skill design-smell-detectorgit clone --depth 1 https://github.com/ArabelaTso/Skills-4-SEWrote 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/arabelatso/skills-4-se/design-smell-detector)<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/design-smell-detector"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/design-smell-detector/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.
<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/design-smell-detector"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/design-smell-detector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00114 | $0.03108 |
| Opus 5 | $0.00057 | $0.01554 |
| Sonnet 5 | $0.00023 | $0.00622 |
| Haiku 4.5 | $0.00011 | $0.00311 |
Grade A, and why
design-smell-detector 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 12d 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 — 582 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Smell Detector
Identify and address design quality issues in code through automated smell detection and refactoring guidance.
Quick Start
Detect Design Smells
# Analyze a single file
python scripts/detect_smells.py src/app.py
# Analyze entire directory
python scripts/detect_smells.py src/
# Output as JSON
python scripts/detect_smells.py src/ --format json
Example Output
Found 5 design smell(s): 1 critical, 3 major, 1 minor
CRITICAL ISSUES:
🔴 src/services.py:45 - God Class
Class 'UserManager' has 25 methods (threshold: 20)
💡 Split into multiple smaller, focused classes
MAJOR ISSUES:
🟠 src/models.py:120 - Low Cohesion
Class 'Order' has low cohesion (score: 0.25)
💡 Group related methods/attributes or split class
🟠 src/utils.py:89 - Long Method
Method 'process_order' has 67 lines (threshold: 50)
💡 Extract smaller methods or refactor
Design Smells Detected
Coupling Smells
High Coupling: Too many dependencies
- Module imports > 20
- Constructor dependencies > 10
- Changes cascade across classes
Feature Envy: Method uses other class more than own
- External access > internal access
- Method should move to envied class
Inappropriate Intimacy: Classes too tightly coupled
- Accessing private fields of other classes
- Excessive use of getters/setters
Cohesion Smells
Low Cohesion: Class members unrelated
- LCOM (Lack of Cohesion) > 0.7
- Methods don't share instance variables
- Class has multiple responsibilities
God Class: Class knows/does too much
- Methods > 20
- Attributes > 15
- Lines of code > 500
Complexity Smells
High Cyclomatic Complexity: Too many decision points
- Complexity > 10
- Deeply nested conditionals
- Many if/else, loops
Long Method: Method too long
- Lines of code > 50
- Multiple responsibilities
- Hard to understand
Size Smells
Long Parameter List: Too many parameters
- Parameters > 5
- Related parameters not grouped
- Method signature hard to understand
What ships with it
3 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.
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.
- 12d ago First seen · 582 lines · 114 tokens per session scan A 9d2db4accde4
design-smell-detector is a skill published in the GitHub repository ArabelaTso/Skills-4-SE (252 stars, last pushed 22d ago), licensed Apache-2.0. It adds 114 tokens to every session and 3,108 once invoked, about $0.0006 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
code-review-web
Review web application code for bugs, security issues, performance problems, and stack-specific anti-patterns. Use this skill whenever the user wants to review code, debug a production issue, investigate a build failure, audit security, or check a PR before merging. Triggers on code review, review my code, debug…
refactor-advisor
A code review helper that finds common design and maintenance problems in a codebase and suggests ways to restructure the code.
pair-programming
A coding partner that writes code and then reviews that code for correctness, security, speed, readability, and reliability. It focuses on issues that can appear in AI-generated code, such as invented APIs or quietly changed requirements.
apply-findings
Apply findings by making the suggested code changes. Applies accepted verdicts, escalates ambiguous findings to the user, and offers to note genuine improvements for later. Use when the user asks to "apply findings", "apply fixes", "apply suggestions", "apply accepted findings", "fix the findings", or "apply the…
java-code-review
Review Java code for bugs, duplicate code, correctness risks, maintainability improvements, and missing tests. By default review files modified in git; when the user explicitly names files, classes, packages, or a diff, review that scope instead. Generate a detailed review.md report with actionable comments and fixes.
simplify-all
Run the code and documentation simplification passes together over one scope, launching every review agent concurrently before applying a single round of fixes. Use when the user asks to "simplify all", "simplify everything", "simplify code and docs", "clean up code and docs", "run both simplify skills", or "simplify…