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/j4flmao/agent-skillsnpx agentmods add skills/j4flmao/agent-skills/oakWrote 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/j4flmao/agent-skills/oak)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/oak"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/oak.svg" alt="Measured on agentmods" height="20"></a>- 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 | $0.00068 | $0.03929 |
| Opus 5 | $0.00034 | $0.01965 |
| Sonnet 5 | $0.00014 | $0.00786 |
| Haiku 4.5 | $0.00007 | $0.00393 |
Grade A, and why
oak-backend 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 8d 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 — 514 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oak Backend
Purpose
Define Oak backend application architecture: Deno-native HTTP server, middleware composition, router pattern, and context management with typed state, composable middleware pipeline, and type-safe routing.
Agent Protocol
Trigger
User request includes: oak, oak backend, deno oak, oak middleware, oak router, deno http, oak context, oak typescript.
Input Context
- Deno version (1.40+)
- Oak version (13.x)
- Language (TypeScript)
- Database (Deno KV, MongoDB via deno_mongo, PostgreSQL via deno_postgres)
- Templating (eta, deno mustache)
- Deployment (Deno Deploy, self-hosted)
Output Artifact
A markdown document containing:
- Project structure
- Router setup (Router class)
- Middleware composition (use, compose)
- Context (c.state, c.cookies, c.send)
- Error handling middleware
- State management (context state)
- Environment configuration (Deno.env)
- Testing (Deno.test, superdeno)
Response Format
Produce the artifact directly. No preamble, no postamble, no explanations. No filler, no hedging. Compress output.
Completion Criteria
- Router separates route definitions from app setup
- Middleware pipeline composed with app.use()
- Error middleware catches all exceptions
- State typed via OakMiddleware type parameter
- Tests use superdeno or fetch-based requests
- Lockfile generated and committed
Max Response Length
4096 tokens
Architecture Decision Trees
Oak vs Hono vs std/http
| Criterion | Oak | Hono | std/http |
|---|---|---|---|
| Middleware ecosystem | Rich (cors, auth, rate-limit, static) | Growing (cors, etag, jwt) | Manual |
| TypeScript context typing | Generic State param |
c.req.valid() |
Manual |
| Router pattern | Router({ prefix }) |
Chained .get().post() |
Switch/match |
| File upload | ctx.request.body({ type: 'form-data' }) |
c.req.parseBody() |
Manual |
| WebSocket | oak_websocket |
Built-in hono/ws |
Manual |
| Community | Mature (12.x, stable) | Growing (4.x) | Std lib |
What ships with it
6 files 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.
- 8d ago First seen · 514 lines · 68 tokens per session scan A 49f1fc00f950
oak-backend is a skill published in the GitHub repository j4flmao/agent-skills (22 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 3,929 once invoked, about $0.0003 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
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…
adapter-express
Mount tRPC as Express middleware with createExpressMiddleware() from @trpc/server/adapters/express. Access Express req/res in createContext via CreateExpressContextOptions. Mount at a path prefix like app.use('/trpc', ...). Avoid global express.json() conflicting with tRPC body parsing for FormData.
trpc-router
Entry point for all tRPC skills. Decision tree routing by task: initTRPC.create(), t.router(), t.procedure, createTRPCClient, adapters, subscriptions, React Query, Next.js, links, middleware, validators, error handling, caching, FormData.
stripe-projects
Use after E2B sandbox/API access has been provisioned through Stripe Projects and the user needs to use the resulting E2B API key with the E2B CLI, JavaScript SDK, Python SDK, or Code Interpreter SDK.
chat-sdk
Build multi-platform chat bots with Chat SDK (chat npm package). Use when developers want to (1) Build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, (2) Use Chat SDK to handle mentions, direct messages, subscribed threads, reactions, slash commands, cards, modals, files, or AI…
nestjs-expert
Creates and configures NestJS modules, controllers, services, DTOs, guards, and interceptors for enterprise-grade TypeScript backend applications. Use when building NestJS REST APIs or GraphQL services, implementing dependency injection, scaffolding modular architecture, adding JWT/Passport authentication, integrating…