type-crusade

type-crusade is a command for Claude Code from btachinardi/church. It costs 33 tokens per session (3,754 once invoked), scanned A, original, MIT.

A command for finding and removing unsafe TypeScript shortcuts such as any and unchecked type casts across a codebase. TypeScript is JavaScript with a system for describing the kinds of values code may use.

In plain words
What is it for?
Use it to inspect selected folders or the whole codebase, check TypeScript configuration, and delegate different kinds of type-safety cleanup.
Why use it?
It helps reveal places where the compiler cannot reliably check the code, especially across a monorepo, which is one repository containing multiple related projects or packages.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is "@myorg/shared-types": ["../../packages/shared-types/src/index.ts"],.

Part of the church plugin — 1 skill, 14 commands, 14 agents shipped together

Good fit Use it to inspect selected folders or the whole codebase, check TypeScript configuration, and delegate different kinds of type-safety cleanup.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/btachinardi/church
agentmods
npx agentmods add commands/btachinardi/church/type-crusade

Made for: Claude Code.

Or install church, the plugin that ships this one along with the rest of its 1 skill, 14 commands, 14 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-crusade

README.md
[![agentmods](https://agentmods.dev/badge/commands/btachinardi/church/type-crusade/github.svg)](https://agentmods.dev/commands/btachinardi/church/type-crusade)
Your own site
<a href="https://agentmods.dev/commands/btachinardi/church/type-crusade"><img src="https://agentmods.dev/badge/commands/btachinardi/church/type-crusade/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 type-crusade

Your own site · 80×15
<a href="https://agentmods.dev/commands/btachinardi/church/type-crusade"><img src="https://agentmods.dev/badge/commands/btachinardi/church/type-crusade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,754 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 $0.00033 $0.03754
Opus 5 $0.00016 $0.01877
Sonnet 5 $0.00007 $0.00751
Haiku 4.5 $0.00003 $0.00375

Measured 10d ago against content hash a6593974a853, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

type-crusade 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 10d 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.

commands/type-crusade.md · 320 lines

How it starts

The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Great Type Crusade

The call has been made. The horns of type safety echo across the codebase. You feel an UNCONTROLLABLE, PRIMAL urge to unleash the TypeScript Purists.

You are the War General. Your soldiers are 4 specialist subagents — ts-any-purist, ts-assertion-purist, ts-guard-purist, and ts-schema-purist. Your enemy is any. Your battlefield is the codebase.

Argument Parsing

  • $ARGUMENTS may contain a path/glob to scope the crusade
  • --scope domain = only src/domains/ directories
  • --scope app = only apps/ directories
  • --scope all (default) = the entire codebase

If no arguments, default to the current working directory with scope all.

Battle Plan

Phase 0: Pre-Flight — Ensure THE LORD Can Speak

Before ANY reconnaissance, verify the monorepo is configured so tsc --noEmit can find all modules:

  1. Check workspace package paths in tsconfig.json:

    • If using moduleResolution: "bundler", workspace packages need explicit paths:
    "paths": {
      "@myorg/shared-types": ["../../packages/shared-types/src/index.ts"],
      "@myorg/shared-types/*": ["../../packages/shared-types/src/*"]
    }
    
    • Without this, THE LORD will cry "Cannot find module" for workspace packages
  2. Verify TypeScript version is 5.0+ for bundler resolution support

  3. Run tsc --noEmit BEFORE the crusade to establish baseline errors

    • If module resolution errors dominate (100+), FIX INFRASTRUCTURE FIRST
    • The crusade fixes CODE sins, not CONFIG sins

Phase 1: Reconnaissance

Before you deploy your army, you must know the battlefield.

CRITICAL: Always exclude node_modules/, dist/, build/, .next/, coverage/ from searches. Use the Grep/Glob tools which respect .gitignore automatically.

  1. Use Glob to find ALL .ts and .tsx files in scope (automatically excludes gitignored dirs)
  2. Use Grep to get a body count of the sins:
    • Count of any occurrences (pattern: \bany\b in .ts/.tsx files)
    • Count of as type assertions (pattern: \bas\b in .ts/.tsx files)
    • Count of @ts-ignore directives
    • Count of @ts-expect-error directives
  3. Present the GRIM STATISTICS to the user in dramatic fashion
  4. Group files by directory/domain into crusade squads (3-6 files per squad)

Read the full file on GitHub · 320 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. 10d ago First seen · 320 lines · 0 tokens per session scan A a6593974a853

Subscribe to this mod's changes

type-crusade is a command published in the GitHub repository btachinardi/church (58 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 3,754 once invoked, about $0.0002 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 2026-08-30.