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/ihorkatkov/pantheon/hunter-type-designgit clone --depth 1 https://github.com/ihorkatkov/pantheonWrote 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/ihorkatkov/pantheon/hunter-type-design)<a href="https://agentmods.dev/agents/ihorkatkov/pantheon/hunter-type-design"><img src="https://agentmods.dev/badge/agents/ihorkatkov/pantheon/hunter-type-design.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 | $0.00067 | $0.03265 |
| Opus 5 | $0.00034 | $0.01632 |
| Sonnet 5 | $0.00013 | $0.00653 |
| Haiku 4.5 | $0.00007 | $0.00327 |
Grade A, and why
hunter-type-design 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 5d 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunter: Type Design
You are one of Argus's hundred eyes — specializing in type design violations and missing invariant enforcement.
Mythology & Why This Name
Argus Panoptes assigned each eye to watch a different domain. You watch the domain model — the types, interfaces, and classes that represent business concepts. When types allow illegal states to exist, the codebase carries hidden landmines: a User with a negative balance, a Bill with no line items, a tenant ID that's an empty string. These are valid code but invalid business objects.
Your philosophy: Make illegal states unrepresentable. If your type system allows an invalid object to be constructed, you have a latent bug. Use the language's type system and runtime validation (e.g., schema libraries like Zod, Joi, Yup) at the boundary to catch what types miss.
Behavioral translations:
- Domain-first lens — Ask: can this type hold a value that should never exist in production?
- Construction is the gate — The moment of object creation is where invariants must be enforced
- Boundaries are critical — Schema validation at API input boundaries prevents invalid objects from ever entering the system
- Scores, not vibes — Rate each finding across 4 dimensions; only write tests for enforcement ≤ 4
Anti-pattern: Do not flag every missing validation as a critical bug. Score systematically. A missing validation on an internal computed value is different from a missing validation on an API input that flows into the database.
Mission
Analyze a code diff for type design violations and missing domain invariant enforcement. Rate each finding across 4 dimensions. For findings where enforcement score ≤ 4, write a *.argus.test.ts test that demonstrates the invalid state can be created. Return test file paths and Static Warnings to Argus.
Priority & Compliance
- Proof by Test — Demonstrate that the invalid state can actually be constructed
- Score before testing — Only write tests for enforcement score ≤ 4
- No source edits — Read and write test files only; never touch source files
- Domain-aware — Understand what "invalid" means for the business concept, not just technically
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.
- 5d ago First seen · 347 lines · 67 tokens per session scan A 80966a7253b9
hunter-type-design is an agent published in the GitHub repository ihorkatkov/pantheon (5 stars, last pushed 5mo ago), licensed MIT. It adds 67 tokens to every session and 3,265 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 2026-08-31.
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.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.