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.
git clone --depth 1 https://github.com/btachinardi/churchWrote 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/commands/btachinardi/church/size-crusade)<a href="https://agentmods.dev/commands/btachinardi/church/size-crusade"><img src="https://agentmods.dev/badge/commands/btachinardi/church/size-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.
<a href="https://agentmods.dev/commands/btachinardi/church/size-crusade"><img src="https://agentmods.dev/badge/commands/btachinardi/church/size-crusade.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00032 | $0.03880 |
| Opus 5 | $0.00016 | $0.01940 |
| Sonnet 5 | $0.00006 | $0.00776 |
| Haiku 4.5 | $0.00003 | $0.00388 |
Grade A, and why
size-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.
How it starts
The opening of the file, as written. The whole thing — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Size Crusade Orchestrator, commanding squads of Size Purist agents in a coordinated assault on bloated files.
THE MISSION
Files grow in the shadows. One line here. A function there. Before anyone notices, innocent modules have become MONSTROSITIES — 1,000-line behemoths that terrify developers and spawn bugs.
Your mission: Find every bloated file. Analyze every monolith. Execute surgical splits.
This is not a gentle refactoring. This is a CRUSADE.
PHASE 1: RECONNAISSANCE
Before deploying surgical teams, you must KNOW THE ENEMY.
Step 1: Parse Arguments
Extract from the user's command:
- Path: Which directory to scan (default: current working directory)
- --threshold N: Override default line limits (applies to generic "ANY file" category)
- --scope: Filter to specific areas
all(default): Scan everythingapi: Only backend files (apps/api, packages if relevant)web: Only frontend files (apps/web, packages/ui)- Custom path: User provides specific directory
- --split: Actually perform splits (default: report-only mode)
Step 2: Count Every File
CRITICAL: ALWAYS exclude node_modules/, dist/, build/, .next/, coverage/ from searches. Use the Glob tool which respects .gitignore automatically, or add explicit exclusions to bash commands.
Use Glob and Bash to find all .ts/.tsx files in scope:
find [PATH] -type f \( -name "*.ts" -o -name "*.tsx" \) \
! -path "*/node_modules/*" ! -path "*/dist/*" ! -path "*/.next/*" ! -path "*/build/*" ! -path "*/coverage/*" \
-exec wc -l {} + | sort -rn
Parse output into structured data:
- File path
- Line count
- File type (classify by suffix: .entity.ts, .controller.ts, .hook.ts, .page.tsx, etc.)
Step 3: Classify and Apply Thresholds
For each file, determine its type and threshold:
| File Type Pattern | Warning | Critical | Emergency |
|---|---|---|---|
| .page.tsx, .layout.tsx | 200 | 350 | 500+ |
| .hook.ts | 150 | 250 | 400+ |
| .entity.ts | 200 | 300 | 500+ |
| .use-case.ts | 150 | 250 | 400+ |
| .controller.ts | 200 | 350 | 500+ |
| .service.ts, .handler.ts | 200 | 300 | 500+ |
| .util.ts, .helper.ts | 100 | 200 | 300+ |
| .spec.ts, .test.ts | 400 | 600 | 1000+ |
| Generic .ts/.tsx | [threshold] | 500 | 1000+ |
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.
- 10d ago First seen · 534 lines · 0 tokens per session scan A 588d51701907
size-crusade is a command published in the GitHub repository btachinardi/church (58 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 3,880 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.