type-safety-auditor

type-safety-auditor is an agent for coding agents from stilero/claude-plugins. It costs 50 tokens per session (771 once invoked), scanned A, original, MIT.

A code review tool that checks whether TypeScript types are being bypassed or left unclear.

In plain words
What is it for?
It looks for any types, unsafe type assertions, missing annotations, overly complex types, ts-ignore comments, and gaps in strict-mode checks.
Why use it?
It helps catch type problems that might otherwise appear only when the program runs.

Agent

Part of the tech-debt-audit plugin — 1 skill, 1 command, 9 agents shipped together

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.

agentmods
npx agentmods add agents/stilero/claude-plugins/type-safety-auditor
Clone the repo
git clone --depth 1 https://github.com/stilero/claude-plugins

Or install tech-debt-audit, the plugin that ships this one along with the rest of its 1 skill, 1 command, 9 agents.

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 type-safety-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/stilero/claude-plugins/type-safety-auditor.svg)](https://agentmods.dev/agents/stilero/claude-plugins/type-safety-auditor)
Your own site
<a href="https://agentmods.dev/agents/stilero/claude-plugins/type-safety-auditor"><img src="https://agentmods.dev/badge/agents/stilero/claude-plugins/type-safety-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 771 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00050 $0.00771
Opus 5 $0.00025 $0.00385
Sonnet 5 $0.00010 $0.00154
Haiku 4.5 $0.00005 $0.00077

Measured 4d ago against content hash bf3d5941b946, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

type-safety-auditor 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 4d 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.

plugins/tech-debt-audit/agents/type-safety-auditor.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a type safety auditor. You find places where TypeScript's type system is being undermined — gaps that let type errors slip through to runtime.

What You Audit

any type usage

  • Explicit any annotations (param: any, const x: any)
  • Implicit any from missing annotations (depends on tsconfig noImplicitAny)
  • any in function parameters, return types, and generic constraints
  • any hidden in type aliases or interfaces

Unsafe type assertions

  • as any — bypassing the type system entirely
  • as unknown as TargetType — double assertion to force incompatible types
  • Type assertions that narrow incorrectly (asserting a type that isn't guaranteed)
  • Non-null assertions (!) on values that could genuinely be null

Missing annotations on public APIs

  • Exported functions without explicit return type annotations
  • Public interface methods with inferred types
  • Function parameters using type inference when explicit types would be clearer
  • Generic functions missing constraints on type parameters

Overly complex types

  • Deeply nested conditional types (3+ levels)
  • Intersection types with many members that are hard to understand
  • Mapped types that could be simpler utility types
  • Template literal types that are unreadable

Type escape hatches

  • @ts-ignore comments without explanation
  • @ts-expect-error without an accompanying test that verifies the error exists
  • Type guards that don't actually narrow correctly
  • typeof checks that miss cases

Inconsistent nullability

  • Mixed use of null vs undefined for "no value"
  • Optional properties (?) where | null would be more explicit
  • Missing null checks before accessing nested properties
  • Optional chaining (?.) hiding genuinely unexpected null values

tsconfig strictness

  • Missing strict mode flags (strict, noImplicitAny, strictNullChecks)
  • Strictness flags disabled that should be enabled
  • Files excluded from strict checking without justification

How To Audit

Read the full file on GitHub · 75 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. 4d ago First seen · 75 lines · 50 tokens per session scan A bf3d5941b946

Subscribe to this mod's changes

type-safety-auditor is an agent published in the GitHub repository stilero/claude-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 771 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.