project-patterns

project-patterns is a skill for Claude Code, Codex from sefaertunc/Worclaude. It costs 20 tokens per session (1,379 once invoked), scanned A, original, MIT.

A project-specific guide to the code structure, naming rules, architecture, and error-handling conventions of the worclaude command-line tool.

In plain words
What is it for?
Use it when adding commands, prompts, core logic, generators, data files, utilities, or tests to the worclaude CLI.
Why use it?
It helps developers make changes that fit the existing project instead of placing logic in the wrong layer or using inconsistent names and file locations.

Skill for Claude CodeCodex

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 skills/sefaertunc/worclaude/project-patterns
Any agent
npx skills add sefaertunc/Worclaude --skill project-patterns
Clone the repo
git clone --depth 1 https://github.com/sefaertunc/Worclaude

Made for: Claude Code, Codex.

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 project-patterns

README.md
[![agentmods](https://agentmods.dev/badge/skills/sefaertunc/worclaude/project-patterns.svg)](https://agentmods.dev/skills/sefaertunc/worclaude/project-patterns)
Your own site
<a href="https://agentmods.dev/skills/sefaertunc/worclaude/project-patterns"><img src="https://agentmods.dev/badge/skills/sefaertunc/worclaude/project-patterns.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,379 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 $0.00020 $0.01379
Opus 5 $0.00010 $0.00690
Sonnet 5 $0.00004 $0.00276
Haiku 4.5 $0.00002 $0.00138

Measured 4d ago against content hash 54abe09b4b7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-patterns 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.

.claude/skills/project-patterns/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Patterns

Architecture Overview

Single-process Node.js CLI tool. No server, no database, no external service dependencies (except npm registry for version checks with 5s timeout). Pure filesystem operations — reads templates, writes scaffolded files, merges with existing user files.

Layer diagram:

CLI Entry (index.js)
  └── Commands (commands/*.js) — orchestration, user flow
        ├── Prompts (prompts/*.js) — Inquirer interactions, isolated from logic
        ├── Core (core/*.js) — business logic, no user interaction*
        ├── Generators (generators/*.js) — produce file content dynamically
        ├── Data (data/*.js) — constants, catalogs, registries
        └── Utils (utils/*.js) — pure helpers, no side effects

*Exception: merger.js calls promptHookConflict() directly — pragmatic compromise.

Key invariant: Commands orchestrate between prompts and core. Prompts never call core directly. Core never prompts the user (except merger.js).

Naming Conventions

  • Files: kebab-case everywhere, no exceptions (agent-routing.js, file-categorizer.js, claude-md-merge.js)
  • Test files: mirror source name + .test.js suffix (merger.test.js, agent-routing-integration.test.js)
  • Functions: camelCase (buildSettingsJson, mergeSettingsPermissionsAndHooks)
  • Constants: UPPER_SNAKE_CASE (UNIVERSAL_AGENTS, AGENT_CATALOG)
  • No private prefix: unexported functions are private by convention — no underscore prefix

File Organization

Layer-based (not feature-based):

src/
├── index.js              # CLI entry point (Commander.js setup)
├── commands/             # One file per CLI command (init, upgrade, status, backup, restore, diff)
├── core/                 # Business logic: scaffolder, merger, detector, backup, config, file-categorizer
├── prompts/              # Inquirer prompt definitions: project-type, tech-stack, agent-selection, conflicts
├── generators/           # Dynamic content builders (agent-routing.js)
├── data/                 # Constants: agents.js (catalogs), agent-registry.js (routing metadata)
└── utils/                # Pure helpers: display.js, file.js, hash.js, time.js, npm.js

templates/                # User-facing template files (quality matters — these ship to users)
├── settings/             # 16 language-specific + base + docker JSON templates
├── agents/               # universal/ (5) + optional/ (18 across 6 categories)
├── commands/             # 10 slash command templates
└── skills/               # universal/ (9) + templates/ (3 placeholder skills)

tests/
├── commands/             # Tests mirror src/ structure
├── core/
├── prompts/
├── utils/
└── fixtures/             # Test projects: fresh-project, existing-project, workflow-project

Read the full file on GitHub · 135 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 · 135 lines · 20 tokens per session scan A 54abe09b4b7b

Subscribe to this mod's changes

project-patterns is a skill published in the GitHub repository sefaertunc/Worclaude (4 stars, last pushed 25d ago), licensed MIT. It adds 20 tokens to every session and 1,379 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 2026-08-31.