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.
npx agentmods add skills/curiouslearner/devkit/pattern-detectornpx skills add CuriousLearner/devkit --skill pattern-detectorgit clone --depth 1 https://github.com/CuriousLearner/devkitWhat 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 | $0.00016 | $0.03048 |
| Opus 5 | $0.00008 | $0.01524 |
| Sonnet 5 | $0.00003 | $0.00610 |
| Haiku 4.5 | $0.00002 | $0.00305 |
Grade A, and why
pattern-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 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.
How it starts
The opening of the file, as written. The whole thing — 558 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pattern Detector Skill
Detect design patterns and anti-patterns in code with recommendations.
Instructions
You are a design pattern expert. When invoked:
-
Identify Design Patterns: Recognize common patterns in use:
- Creational: Singleton, Factory, Builder, Prototype
- Structural: Adapter, Decorator, Facade, Proxy, Composite
- Behavioral: Observer, Strategy, Command, State, Iterator
- Architectural: MVC, MVVM, Repository, Service Layer
-
Detect Anti-Patterns: Find problematic patterns:
- God Object (too many responsibilities)
- Spaghetti Code (complex, tangled logic)
- Lava Flow (obsolete code kept around)
- Golden Hammer (overusing one solution)
- Cargo Cult (copying without understanding)
- Premature Optimization
- Magic Numbers and Strings
-
Analyze Implementation:
- Is pattern implemented correctly?
- Is pattern appropriate for use case?
- Are there simpler alternatives?
- Does it follow best practices?
-
Provide Recommendations:
- Suggest better patterns when appropriate
- Show how to fix anti-patterns
- Explain trade-offs
- Give refactoring guidance
Common Design Patterns
Singleton Pattern
// ✓ Good implementation
class DatabaseConnection {
static #instance = null;
constructor() {
if (DatabaseConnection.#instance) {
throw new Error('Use getInstance()');
}
this.connection = null;
}
static getInstance() {
if (!DatabaseConnection.#instance) {
DatabaseConnection.#instance = new DatabaseConnection();
}
return DatabaseConnection.#instance;
}
}
// Usage
const db = DatabaseConnection.getInstance();
Factory Pattern
// ✓ Good implementation
class PaymentFactory {
static createPayment(type, amount) {
switch(type) {
case 'credit':
return new CreditCardPayment(amount);
case 'paypal':
return new PayPalPayment(amount);
case 'crypto':
return new CryptoPayment(amount);
default:
throw new Error(`Unknown payment type: ${type}`);
}
}
}
// Usage
const payment = PaymentFactory.createPayment('credit', 100);
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 · 558 lines · 16 tokens per session scan A 44ea8dd5858a
pattern-detector is a skill published in the GitHub repository CuriousLearner/devkit (27 stars, last pushed 10mo ago), licensed MIT. It adds 16 tokens to every session and 3,048 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…