Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sefaertunc/Worclaudenpx agentmods add skills/sefaertunc/worclaude/project-patternsWrote 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/skills/sefaertunc/worclaude/project-patterns)<a href="https://agentmods.dev/skills/sefaertunc/worclaude/project-patterns"><img src="https://agentmods.dev/badge/skills/sefaertunc/worclaude/project-patterns/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/skills/sefaertunc/worclaude/project-patterns"><img src="https://agentmods.dev/badge/skills/sefaertunc/worclaude/project-patterns.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 | $0.00020 | $0.01379 |
| Opus 5.5 | $0.00008 | $0.00552 |
| Sonnet 5.5 | $0.00004 | $0.00276 |
| Haiku 4.5 | $0.00002 | $0.00138 |
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 1mo 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 — 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.jssuffix (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
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.
- 1mo ago First seen · 135 lines · 20 tokens per session scan A 54abe09b4b7b
project-patterns is a skill published in the GitHub repository sefaertunc/Worclaude (4 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 1,379 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-rust
This is an OMH rust workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…
authentication-patterns
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.