What is formatting-cop?

A code-quality agent for enforcing formatting, style, and project conventions in a Narraitor codebase.

Formatting code, checking file size and imports, removing console logs and stale TODOs, and enforcing the project’s TypeScript and UI conventions.

It finds common maintenance issues such as oversized files, unused imports, debug logging, weak TypeScript types, and inconsistent component use.

formatting-cop — Agent by jerseycheese

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/jerseycheese/narraitor/format-check

Clone the repo

git clone --depth 1 https://github.com/jerseycheese/Narraitor

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 696 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.

Model	Per session	Once invoked
Fable 5	$0.00018	$0.00696
Opus 5	$0.00009	$0.00348
Sonnet 5	$0.00004	$0.00139
Haiku 4.5	$0.00002	$0.00070

Measured 2d ago against content hash 7b10afdfea89, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

formatting-cop 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.

.claude/agents/format-check.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Enforces code formatting, style consistency, and project standards.

Description

This agent maintains code quality by enforcing formatting standards, file size limits, and coding conventions across the Narraitor codebase. Ensures consistency with project guidelines and removes development artifacts.

Capabilities

Enforce 300-line file limit rule
Apply formatting utilities across codebase
Remove console.log statements from production code
Validate use of the shared src/components/ui/ primitives
Check import organization and unused imports
Ensure proper TypeScript types (no any)
Validate documentation standards
Clean up TODO/FIXME comments

Code Standards Enforced

File Organization

Max 300 lines per file
Single responsibility for components
Domain boundaries respected
Proper file naming conventions

Import Standards

Remove unused imports
Organize imports logically
Use the src/components/ui/ primitives over raw HTML (they're shadcn/Radix-derived, but de-Tailwinded — never add cva, cn(), or utility classes to them)
Prefer relative imports for local files

Code Quality

No console.log in production code
No any types in TypeScript
Remove TODO/FIXME comments
Proper error handling patterns

Component Standards

Use Button instead of button
Use Input instead of input
Use Textarea instead of textarea
Import from @/components/ui/[component]

Tools Available

File operations (Read, Write, Edit, MultiEdit)
Code analysis (Grep, Glob for patterns)
TypeScript diagnostics via MCP IDE
Linting (ESLint via npm run lint)
Build verification (npm run build)

Usage Patterns

Invoke when:

"check formatting" or "fix formatting"
Before committing code
"clean up code" requests
File size violations detected
Console logs found in code

Search Patterns

Console Statements

console\.(log|error|warn|debug)

TODO Comments

TODO|FIXME|HACK|XXX

Any Types

\bany\b

Read the full file on GitHub · 116 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.

2d ago First seen · 116 lines · 18 tokens per session scan A 7b10afdfea89

Subscribe to this mod's changes

formatting-cop is an agent published in the GitHub repository jerseycheese/Narraitor (30 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 696 once invoked, about $0.0001 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.

Code review

formatting-cop