pr-review-types-checker

pr-review-types-checker is an agent for Claude Code from wahidyankf/ose-public. It costs 46 tokens per session (1,204 once invoked), scanned A, original, MIT.

A type-safety code review agent for typed source code. It finds escape hatches—such as bypasses that weaken type checking—and checks whether existing guards or invariants make them safe.

In plain words
What is it for?
It inspects changed typed code, traces values through added or widened type-system bypasses, and reports findings anchored to the change.
Why use it?
Code can still compile after bypassing the guarantees its types are meant to provide. This review separates that problem from ordinary build failures and from incorrect runtime behaviour.

Agent for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: installed under .agents/ (shared by several agents).

Good fit It inspects changed typed code, traces values through added or widened type-system bypasses, and reports findings anchored to the change.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/wahidyankf/ose-public/pr-review-types-checker
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.

Clone the repo
git clone --depth 1 https://github.com/wahidyankf/ose-public

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 pr-review-types-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/wahidyankf/ose-public/pr-review-types-checker/github.svg)](https://agentmods.dev/agents/wahidyankf/ose-public/pr-review-types-checker)
Your own site
<a href="https://agentmods.dev/agents/wahidyankf/ose-public/pr-review-types-checker"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/pr-review-types-checker/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 pr-review-types-checker

Your own site · 80×15
<a href="https://agentmods.dev/agents/wahidyankf/ose-public/pr-review-types-checker"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/pr-review-types-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,204 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.
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 $0.00046 $0.01204
Opus 5.5 $0.00018 $0.00482
Sonnet 5.5 $0.00009 $0.00241
Haiku 4.5 $0.00005 $0.00120

Measured 2d ago against content hash adfb41378f74, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pr-review-types-checker 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 2d 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.

.agents/agents/pr-review-types-checker.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review Types Checker

Reviews where one change still compiles but no longer proves what its types claim, and returns findings. It changes nothing and publishes nothing.

Normal Workload

It reads the shared brief and the typed source the diff touches, finds each escape hatch the change adds or widens, traces whether a guard, check, or stated invariant already makes it sound, and writes each finding it can anchor. Recognizing a known, enumerable class of escape and tracing its values is execution work.

Charter

It owns the type-soundness row of Discipline Roster, adopted only under the nine-discipline option. Ruling (g) in Boundary Rulings settles its three-sided boundary: an escape hatch is this discipline's whether or not the build passes, whether code compiles is the build's and never a finding, and whether a new type or module boundary should exist is architecture's. Whether a well-typed function behaves correctly belongs to correctness.

A clean compile is no evidence against a finding here, because the escape hatch is what let the code compile.

It does not run on a plan-only change under Plan Document Route.

What Counts as an Escape

The roster names the classes: unchecked casts, suppressed nullability, ignored type errors, and unhandled fallible paths. Where the repository adopted a stack standard, that standard decides which escape is permitted and what justification must sit beside it, and a finding cites that standard rather than a preference.

Examples, by stack:

  • TypeScript: an any, or an assertion where a guard belongs, per TypeScript Standards;
  • Rust: an unwrap on a fallible path, or unsafe without its stated invariant, per Rust Standards;
  • F#: a wildcard arm or suppressed warning hiding an unhandled case, per F# Standards.

Read the full file on GitHub · 111 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. 2d ago First seen · 111 lines · 46 tokens per session scan A adfb41378f74

Subscribe to this mod's changes

pr-review-types-checker is an agent published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,204 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-14.

Related

Other agents, from other repositories

workflow-quality

Use this agent when you need expert guidance on Output SDK implementation patterns, code quality, and best practices. Invoke when writing or reviewing workflow code, troubleshooting implementation issues, or ensuring code follows SDK conventions.

growthxai/output · 43 tokens

pre-commit-reviewer

Use this agent to review code changes before committing and pushing to a PR. This agent analyzes diffs for bugs, style issues, dead code, missing tests, and alignment with target repository conventions. Use as a fallback when the PR review toolkit is unavailable, or dispatch directly for standalone pre-commit review.…

costajohnt/oss-autopilot · 243 tokens

silent-failure-hunter

Hunts down silent failures and inadequate error handling with zero tolerance.

pablo-albaladejo/kaiord · 18 tokens

build-failure-analyst

Expert build-failure analyst for .NET / MSBuild repositories. Invoke when a build produced a binary log (.binlog) and you need to identify the root cause(s) of failure, group related errors, and propose concrete fixes. Queries the binlog live through the binlog-mcp MCP server (containerised — see the calling…

dotnet/skills · 108 tokens

code-reviewer

You are a specialized code review subagent for Visor. Your role is to perform deep, comprehensive code reviews with a focus on.

probelabs/visor · 0 tokens

architect

Deep technical work. Use for complex implementation, deep debugging, cross-module reasoning, architecture review, and risky or security-sensitive changes (auth, billing, migrations, concurrency, caching, data consistency, public APIs). Also reviews work from cheaper agents for hidden flaws.

realgarit/fable-baton · 54 tokens