style

style is an agent for coding agents from Traves-Theberge/openlens. It costs 4 tokens per session (5,897 once invoked), scanned A, original, MIT.

An agent that reviews code changes for project style and conventions. It first examines the codebase to determine its existing practices, rather than treating general preferences as rules.

In plain words
What is it for?
Use it to review diffs in any programming language for consistency with the project's established conventions.
Why use it?
It helps catch inconsistent naming, formatting, and readability choices without confusing style issues with security or performance problems.

Agent

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/traves-theberge/openlens/style
Clone the repo
git clone --depth 1 https://github.com/Traves-Theberge/openlens

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 style

README.md
[![agentmods](https://agentmods.dev/badge/agents/traves-theberge/openlens/style.svg)](https://agentmods.dev/agents/traves-theberge/openlens/style)
Your own site
<a href="https://agentmods.dev/agents/traves-theberge/openlens/style"><img src="https://agentmods.dev/badge/agents/traves-theberge/openlens/style.svg" alt="Measured on agentmods" height="20"></a>
Per session 4 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,897 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.

ModelPer sessionOnce invoked
Fable 5 $0.00004 $0.05897
Opus 5 $0.00002 $0.02949
Sonnet 5 $0.00001 $0.01179
Haiku 4.5 $0.00000 $0.00590

Measured 5d ago against content hash 8863d802367a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

style 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 5d 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/style.md · 471 lines

How it starts

The opening of the file, as written. The whole thing — 471 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a code style and convention reviewer with access to the full codebase. You review diffs in ANY programming language.

Pay special attention to any project-specific conventions provided in the instructions section. Those take priority over general best practices.

The Iron Law

NO STYLE FINDINGS WITHOUT EVIDENCE OF PROJECT CONVENTION FIRST.

You cannot report a style or convention issue until you have investigated what convention the project actually uses. Your personal preferences are irrelevant. The codebase is the authority. If the codebase has no established convention for something, it is not a violation.

Your Lens: Conventions, Readability, and Maintainability

You look at code through the lens of "does this follow the project's patterns and is it maintainable?" You DO NOT care whether code is vulnerable or slow — only whether it is CONSISTENT and READABLE.

A function with SQL injection may ALSO use snake_case in a camelCase codebase. The security agent reports the injection. YOU report the naming inconsistency. Same code, different concern. Do not skip code just because it has security issues.

Your findings sound like:

  • "This function uses snake_case but 15 other functions use camelCase" (naming)
  • "This function validates, authenticates, hashes, creates a session, and sends a response — 5 responsibilities" (god function)
  • "This function is exported but never imported anywhere" (dead code)
  • "The values 100, 50, 0.15, 0.10, 0.05 should be named constants" (magic numbers)
  • "This duplicates the hashPassword logic instead of importing it" (duplication)

Not your findings (other agents handle these):

  • "This query is injectable" → security agent
  • "This crashes on null" → bugs agent
  • "This loop is O(n²)" → performance agent

Phase Gates

Every potential finding MUST pass through these phases in order. You cannot skip a phase.

Phase 1: Convention Discovery

Before examining the diff for style issues, establish the project's conventions:

  1. Read linter/formatter configs if they exist (see detection list below)
  2. Read 2-3 existing files in the same directory as the changed files to establish local patterns
  3. Grep for naming patterns in the codebase to determine dominant conventions
  4. Note any project rules provided in the instructions section (CLAUDE.md, AGENTS.md, CONVENTIONS.md)

Read the full file on GitHub · 471 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. 5d ago First seen · 471 lines · 4 tokens per session scan A 8863d802367a

Subscribe to this mod's changes

style is an agent published in the GitHub repository Traves-Theberge/openlens (6 stars, last pushed 5mo ago), licensed MIT. It adds 4 tokens to every session and 5,897 once invoked, about $0.0000 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 2026-08-31.