evolve-type-safety-audit

evolve-type-safety-audit is an agent for Claude Code from mickeyyaya/evolve-loop. It costs 84 tokens per session (1,491 once invoked), scanned A, original, Apache-2.0.

A review agent that checks whether changed code uses strong, explicit types and represents its rules in the type system. It looks for escape hatches such as any, unchecked casts, and boundaries whose rules exist only in comments.

In plain words
What is it for?
Use it after builds involving refactors or large changes to review type design without editing source code.
Why use it?
It catches bugs that a compiler could have prevented when values are too loosely typed or assumptions are hidden outside the code's types.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the evo plugin — 32 skills, 33 commands, 99 agents, 3 hooks shipped together

Good fit Use it after builds involving refactors or large changes to review type design without editing source code.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mickeyyaya/evolve-loop/evolve-type-safety-audit
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/mickeyyaya/evolve-loop

Made for: Claude Code.

Or install evo, the plugin that ships this one along with the rest of its 32 skills, 33 commands, 99 agents, 3 hooks.

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 evolve-type-safety-audit

README.md
[![agentmods](https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-type-safety-audit/github.svg)](https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-type-safety-audit)
Your own site
<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-type-safety-audit"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-type-safety-audit/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 evolve-type-safety-audit

Your own site · 80×15
<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-type-safety-audit"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-type-safety-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,491 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 $0.00084 $0.01491
Opus 5.5 $0.00034 $0.00596
Sonnet 5.5 $0.00017 $0.00298
Haiku 4.5 $0.00008 $0.00149

Measured 1mo ago against content hash aa60d39a26df, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

evolve-type-safety-audit 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 1mo 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/evolve-type-safety-audit.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evolve Type-Safety Auditor

You are the Type-Safety Auditor in the Evolve Loop pipeline — an Evaluate-archetype gate the advisor inserts after Build, on refactor cycles and on any large diff (broad gate: it fires on diff size, not only its goal type). You are an independent skeptic: assume every changed type surface leaks a bug the compiler should have caught — an escape hatch that defeats static checking, or a boundary whose invariant lives only in a comment — until the types prove that illegal state is unrepresentable. You operationalize Core Rules 1 and 8 (think before coding; read the real types) as a hard gate. You never edit source.

You audit type design, not behavior. You ask: Where did this diff swap a checked type for any/interface{}/unsafe? Where does a cast or assertion assume a shape the type system was never told about? Which boundary accepts a value whose legal domain is narrower than its declared type, with no newtype/enum/constructor to enforce it?

Derived skill: type-system-patterns / type-design-analyzer (make-illegal-states-unrepresentable; parse-don't-validate).

You are NOT smell-scan (which ranks structural debt — long methods, duplication, coupling — across the module) and NOT contract-fuzz-probe (which runtime-probes untrusted input boundaries by feeding malformed payloads). The risk THIS phase owns and they do not: a bug the compiler should have caught but a weakened static type lets through — an escape hatch or an un-encoded invariant — found by static type-design reading alone, no execution.

Pipeline Position

Build → [Type-Safety Audit] → (audit / ship)
            ▲ inserted after build on refactor cycles OR any large diff
  • Receives from Build/Scout: build-report.md, build.files_touched, and the changed source tree (the diff). Reads the surrounding types to judge each surface.
  • Delivers: type-safety-audit-report.md — a PASS/WARN/FAIL verdict gating entry to audit/ship.

Read the full file on GitHub · 47 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. 1mo ago First seen · 47 lines · 84 tokens per session scan A aa60d39a26df

Subscribe to this mod's changes

evolve-type-safety-audit is an agent published in the GitHub repository mickeyyaya/evolve-loop (6 stars, last pushed today), licensed Apache-2.0. It adds 84 tokens to every session and 1,491 once invoked, about $0.0003 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 2026-09-03.

Related

Other agents, from other repositories

architect

Maps component boundaries, data flow, interfaces, and dependency graph.

greglas75/zuvo · 15 tokens

behavior-auditor

Logic correctness, error handling, async safety, and CQ3-CQ10 checks on changed production files.

greglas75/zuvo · 26 tokens

eval-failure-analyzer

Analyze Logic-Lens benchmark/eval failures. Use after running content-evals, or when pointed at a skills-workspace/iteration- directory or a benchmarks/runs/ entry, to cluster failing cases by failure mode, map each mode to the specific eval IDs, and propose concrete SKILL.md disambiguation-rule changes. Read-only…

hyhmrright/logic-lens · 90 tokens

code-reviewer

Reviews completed implementation for governing-source compliance, scope economy, repository quality policy, and material code correctness. Use after implementation or when review/implementation check/compliance is requested.

shinpr/claude-code-workflows · 38 tokens

investigator

Comprehensively collects problem-related information and creates evidence matrix. Use PROACTIVELY when bug/error/issue/defect/not working/strange behavior is reported. Reports observations and evidence for downstream cause verification.

shinpr/claude-code-workflows · 46 tokens

fec-performance-optimizer

Front-end performance analysis and optimization specialization: Core Web Vitals, packaging volume, runtime and rendering, network and cache, memory leak troubleshooting; can cooperate with Lighthouse, Bundle analysis and Profiler. Use it when users mention page slowness, lag, first screen, package size, poor…

bovinphang/frontend-craft · 72 tokens