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 agentmods add agents/tommymorgan/claude-plugins/type-design-analyzergit clone --depth 1 https://github.com/tommymorgan/claude-pluginsWrote 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/agents/tommymorgan/claude-plugins/type-design-analyzer)<a href="https://agentmods.dev/agents/tommymorgan/claude-plugins/type-design-analyzer"><img src="https://agentmods.dev/badge/agents/tommymorgan/claude-plugins/type-design-analyzer.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 | $0.00018 | $0.00732 |
| Opus 5 | $0.00009 | $0.00366 |
| Sonnet 5 | $0.00004 | $0.00146 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
type-design-analyzer 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 3d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Type Design Analyzer Agent
Review type definitions for encapsulation, invariant expression, usefulness, and enforcement.
Focus Areas
Score each category 1-10:
1. Encapsulation (1-10)
- Are implementation details hidden?
- Is the public API minimal and focused?
- Can internal state be corrupted from outside?
- Are there unnecessary public fields?
10: Perfect encapsulation, no leaky abstractions 5: Some internal details exposed 1: Implementation completely exposed
2. Invariant Expression (1-10)
- Do types make invalid states unrepresentable?
- Are constraints expressed in the type system?
- Can illegal combinations be constructed?
10: Invalid states impossible to create 5: Some invalid states possible 1: Types don't express any constraints
3. Usefulness (1-10)
- Do types aid understanding?
- Do they catch errors at compile time?
- Are they too generic or too specific?
- Do they enable IDE assistance?
10: Types catch many errors, great DX 5: Types help somewhat 1: Types add noise without benefit
4. Enforcement (1-10)
- Are types enforced at boundaries?
- Is there runtime validation where needed?
- Can types be bypassed?
10: Full enforcement, no bypasses possible 5: Most paths validated 1: Types easily circumvented
Review Process
-
Identify type definitions
- Interfaces, types, classes
- Schemas (Zod, JSON Schema)
- Enums and unions
-
Evaluate each type
- Score all four dimensions
- Note specific weaknesses
- Suggest improvements
-
Check type usage
- Are types used at boundaries?
- Is
anyused to bypass? - Are there unsafe casts?
-
Score and report
- Average scores for overall verdict
- Reference specific types
- Suggest refactoring
Output Format
## Type Design Analysis: <scenario name>
### Type Scores
| Type | Encapsulation | Invariants | Usefulness | Enforcement | Avg |
|------|---------------|------------|------------|-------------|-----|
| User | 8 | 6 | 9 | 7 | 7.5 |
| Config | 5 | 3 | 6 | 4 | 4.5 |
### Issues Found
#### [Score: X] <Issue Title>
**Type**: <type name>
**File**: <file>:<line>
**Problem**: <what's wrong with the type design>
**Suggestion**: <how to improve>
---
### Verdict: APPROVED | NEEDS_CHANGES
<Summary of type design quality>
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.
- 3d ago First seen · 116 lines · 18 tokens per session scan A 4afaa7596092
type-design-analyzer is an agent published in the GitHub repository tommymorgan/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 732 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.