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/wasintoh/toh-framework/dev-engineernpx skills add wasintoh/toh-framework --skill dev-engineergit clone --depth 1 https://github.com/wasintoh/toh-frameworkWhat 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 | $0.00075 | $0.03764 |
| Opus 5 | $0.00037 | $0.01882 |
| Sonnet 5 | $0.00015 | $0.00753 |
| Haiku 4.5 | $0.00007 | $0.00376 |
Grade A, and why
dev-engineer 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 — 592 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Engineer
Add brains to the beauty. Connect logic to UI seamlessly.
<core_principle>
The Enhancement Promise
UI exists (from ui-first-builder) → Add state/logic → UI becomes functional
We don't create UI. We make existing UI work. </core_principle>
<default_to_action> NEVER ask:
- "What state management should I use?" → Use Zustand (our standard)
- "What validation library?" → Use Zod (our standard)
- "What form library?" → Use React Hook Form (our standard)
ALWAYS do:
- When scaffolding a NEW project, run
npm view [package] versionfor each dependency to get the latest STABLE before pinning — check live, never hardcode a version number here (the framework must not go stale; internalize the principle, not the digits) - Create TypeScript types FIRST
- Create Zustand store for state
- Add form validation with Zod
- Prepare CRUD operations (mock first, real later) </default_to_action>
<typescript_patterns>
Type Definitions
Location
Always create: src/types/index.ts or src/types/[feature].ts
Pattern
// src/types/index.ts
// Entity types
export interface User {
id: string
name: string
email: string
role: "admin" | "user" | "editor"
avatar?: string
createdAt: Date
updatedAt: Date
}
export interface Product {
id: string
name: string
description: string
price: number
stock: number
category: string
images: string[]
isActive: boolean
createdAt: Date
updatedAt: Date
}
// Form types (for create/update)
export type CreateProductInput = Omit<Product, "id" | "createdAt" | "updatedAt">
export type UpdateProductInput = Partial<CreateProductInput>
// API response types
export interface PaginatedResponse<T> {
data: T[]
total: number
page: number
pageSize: number
totalPages: number
}
// Common utility types
export type ID = string | number
export type Nullable<T> = T | null
Naming Conventions
- Entity:
User,Product,Order(singular, PascalCase) - Input:
CreateUserInput,UpdateUserInput - Response:
UserResponse,PaginatedResponse<User> - Props:
UserCardProps,ProductListProps</typescript_patterns>
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 · 592 lines · 75 tokens per session scan A 80d7c38df4a4
dev-engineer is a skill published in the GitHub repository wasintoh/toh-framework (95 stars, last pushed 6d ago), licensed MIT. It adds 75 tokens to every session and 3,764 once invoked, about $0.0004 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
smoke-test
End-to-end smoke test skill for DeerFlow. Guides through: 1) Pulling latest code, 2) Docker OR Local installation and deployment (user preference, default to Local if Docker network issues), 3) Service availability verification, 4) Health check, 5) Final test report. Use when the user says "run smoke test", "smoke…
image-generation
Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
skill-reviewer
Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence. Invoke when users ask to audit, grade, or production-check an existing skill.
surprise-me
Create a delightful, unexpected "wow" experience for the user by dynamically discovering and creatively combining other enabled skills. Triggers when the user says "surprise me" or any request expressing a desire for an unexpected creative showcase. Also triggers when the user is bored, wants inspiration, or asks for…