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 skills add bobmatnyc/claude-mpm-skills --skill hono-coregit clone --depth 1 https://github.com/bobmatnyc/claude-mpm-skillsWrote 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/bobmatnyc/claude-mpm-skills/hono-core)<a href="https://agentmods.dev/skills/bobmatnyc/claude-mpm-skills/hono-core"><img src="https://agentmods.dev/badge/skills/bobmatnyc/claude-mpm-skills/hono-core/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/bobmatnyc/claude-mpm-skills/hono-core"><img src="https://agentmods.dev/badge/skills/bobmatnyc/claude-mpm-skills/hono-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00026 | $0.03122 |
| Opus 5.5 | $0.00010 | $0.01249 |
| Sonnet 5.5 | $0.00005 | $0.00624 |
| Haiku 4.5 | $0.00003 | $0.00312 |
Grade A, and why
hono-core 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 — 511 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hono - Ultrafast Web Framework
Overview
Hono is a small, simple, and ultrafast web framework built on Web Standards. It runs on Cloudflare Workers, Deno, Bun, Node.js, and more with the same codebase. The name means "flame" in Japanese.
Key Features:
- Built on Web Standards (Request/Response/fetch)
- Multi-runtime: Cloudflare Workers, Deno, Bun, Node.js, Vercel, AWS Lambda
- Ultrafast routing with RegExpRouter
- First-class TypeScript support
- Lightweight (~14KB minified)
- Rich middleware ecosystem
Installation:
# Create new project (recommended)
npm create hono@latest my-app
# Or install in existing project
npm install hono
# Runtime-specific adapters
npm install @hono/node-server # Node.js
When to Use This Skill
Use Hono when:
- Building APIs for edge/serverless environments (Cloudflare Workers, Vercel Edge)
- Need multi-runtime portability (same code on Bun, Deno, Node.js)
- Want TypeScript-first development with excellent type inference
- Building lightweight, high-performance APIs
- Need built-in middleware for common patterns (CORS, auth, compression)
Hono vs Other Frameworks:
- Hono: Multi-runtime, Web Standards, ultrafast, edge-optimized
- Express: Node.js only, larger ecosystem, slower
- Fastify: Node.js only, schema-based, good performance
- Elysia: Bun only, excellent performance, different API style
Core Concepts
Creating an Application
import { Hono } from 'hono'
const app = new Hono()
app.get('/', (c) => c.text('Hello Hono!'))
export default app
With TypeScript Generics (for bindings/variables):
type Bindings = {
DATABASE_URL: string
API_KEY: string
}
type Variables = {
user: { id: string; name: string }
}
const app = new Hono<{ Bindings: Bindings; Variables: Variables }>()
The Context Object (c)
The context c provides access to request data and response methods:
app.get('/users/:id', async (c) => {
// Request data
const id = c.req.param('id') // Path parameter
const query = c.req.query('sort') // Query parameter ?sort=asc
const queries = c.req.queries('tags') // Multiple: ?tags=a&tags=b
const header = c.req.header('Authorization')
const body = await c.req.json() // JSON body
const form = await c.req.formData() // Form data
// Environment (Cloudflare Workers bindings)
const db = c.env.DATABASE_URL
// Custom variables (set by middleware)
const user = c.get('user')
// Response methods
return c.text('Plain text')
return c.json({ id, name: 'User' })
return c.html('<h1>Hello</h1>')
return c.redirect('/login')
return c.notFound()
})
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 511 lines · 26 tokens per session scan A 26107a1a934c
hono-core is a skill published in the GitHub repository bobmatnyc/claude-mpm-skills (78 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 3,122 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 2026-08-30.
Other skills, from other repositories
add-a-lib
Scaffold a new shared library under libs/ in the builders-stack monorepo. Use when code is needed in two or more places (apps or services) and should become a single source of truth consumed by package name. Covers the package.json, tsconfig, the one-public-door src/index.ts barrel, and wiring it into a consumer…
nifra
Use when writing, reviewing, or debugging code in a Nifra project (@nifrajs/ packages, nifra CLI, server()/defineContract, loaders and actions, file routes under routes/). Explains how to reach Nifra's live MCP tools so signatures come from the installed version instead of memory, and which sibling skill to load for…
tsq-hono
A set of backend development guidelines for Hono, a lightweight web framework for Node.js. It covers API routes, input checking, error handling, authentication, configuration, and clean separation of application layers.
sora-client
A typed TypeScript client for calling Sora tools as functions from code. It can call tools for tasks such as search, fetching page text, addresses, and weather, then filter the results before returning selected fields.
sora-client
A typed TypeScript client for calling Sora tools as functions from code. It can call tools for tasks such as search, fetching page text, addresses, and weather, then filter the results before returning selected fields.
bun
Bun all-in-one JavaScript runtime and toolkit reference. Covers runtime APIs (file I/O, HTTP server, SQLite, shell), ultra-fast package manager, built-in bundler with plugins, test runner with mocking, TypeScript support, and Node.js compatibility.