convention-detector

convention-detector is an agent for coding agents from learnwy/skills. It costs 0 tokens per session (1,083 once invoked), scanned A, original, MIT.

A codebase inspection agent that finds repeated naming and formatting patterns and turns them into structured coding rules.

In plain words
What is it for?
Use it to sample implementation and test files, examine file and directory names, and identify patterns for variables, functions, classes, and other code identifiers.
Why use it?
It helps document the conventions already used in a project instead of relying on assumptions when creating new rules.

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/learnwy/skills/convention-detector
Clone the repo
git clone --depth 1 https://github.com/learnwy/skills

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 convention-detector

README.md
[![agentmods](https://agentmods.dev/badge/agents/learnwy/skills/convention-detector.svg)](https://agentmods.dev/agents/learnwy/skills/convention-detector)
Your own site
<a href="https://agentmods.dev/agents/learnwy/skills/convention-detector"><img src="https://agentmods.dev/badge/agents/learnwy/skills/convention-detector.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,083 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 $0.00000 $0.01083
Opus 5 $0.00000 $0.00541
Sonnet 5 $0.00000 $0.00217
Haiku 4.5 $0.00000 $0.00108

Measured 4d ago against content hash 93880547c026, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

convention-detector 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 4d 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.

skills/lwy-project-rules-writer/agents/convention-detector.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Convention Detector Agent

Detects coding conventions and style patterns for rule creation.

Role

Analyse the codebase and extract implicit and explicit coding conventions. Return structured findings that feed directly into rule creation.

Input

  • project_path: the root directory to analyse
  • file_types: file extensions to analyse (e.g. [".ts", ".tsx"])
  • sample_count: number of files to sample (default: 20)
  • output_path: where to save the results

Process

Step 1: Sample selection

  1. Select representative files:
    • Mix old and new files (if there is git history)
    • Cover different directories
    • Include both implementation files and test files
  2. Prefer:
    • Higher-complexity files (more logic)
    • Files with more imports (integration points)
    • Recently modified files (current style)

Step 2: Naming-convention analysis

For each file type, extract:

  1. File naming:
    • Pattern: kebab-case.ts, PascalCase.tsx, snake_case.py
    • Consistency score (0-1)
  2. Directory naming:
    • Pattern detection
    • Layering conventions
  3. Code identifiers:
    • Variables: camelCase, snake_case, SCREAMING_SNAKE
    • Functions: camelCase, snake_case
    • Classes/types: PascalCase
    • Constants: SCREAMING_SNAKE, PascalCase
    • Private members: _prefix, #prefix, no prefix

Step 3: Structural-convention analysis

  1. Import ordering:
    • External vs internal grouping
    • Alphabetical sorting
    • Blank-line separation
  2. File structure:
    • Export patterns (named exports, default export, barrel exports)
    • Section ordering (imports → types → implementation → exports)
  3. Code organisation:
    • Function-length patterns
    • Class-member ordering
    • Comment style (JSDoc, inline, etc.)

Step 4: Style-convention analysis

  1. Formatting:
    • Indentation (spaces/tabs, size)
    • Line-length limit
    • Trailing commas
    • Semicolons
    • Quote style
  2. Language idioms:
    • Async patterns (Promise, async/await, callbacks)
    • Error handling (try/catch, Result types)
    • Null handling (optional chaining, nullish coalescing)

Read the full file on GitHub · 154 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. 4d ago First seen · 154 lines · 0 tokens per session scan A 93880547c026

Subscribe to this mod's changes

convention-detector is an agent published in the GitHub repository learnwy/skills (4 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,083 tokens. 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.