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/denoWrote 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/deno)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/deno"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/deno/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/j4flmao/agent-skills/deno"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/deno.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00138 | $0.02950 |
| Opus 5.5 | $0.00055 | $0.01180 |
| Sonnet 5.5 | $0.00028 | $0.00590 |
| Haiku 4.5 | $0.00014 | $0.00295 |
Grade A, and why
deno 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 today.
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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deno
Purpose
Build TypeScript services on Deno 2 with least-privilege permissions, JSR-first dependencies, built-in tooling (fmt, lint, test, check, compile) and a choice of bare Deno.serve, Hono, Oak or Fresh.
Agent Protocol
Trigger
Exact user phrases: "deno", "deno 2", "deno.json", "deno task", "deno compile", "deno test", "Deno.serve", "Deno KV", "JSR", "deno permissions", "Fresh framework".
Input Context
- Deno version (assume 2.x) and deployment target (Deno Deploy, Docker, compiled binary).
- Framework (bare
Deno.serve, Hono, Oak, Fresh). - Data store (Deno KV, PostgreSQL via
npm:pg/jsr:@db/postgres, Redis). - Required permissions (net, read, write, env, run, ffi).
Output Artifact
deno.json, server code, tests and run/deploy commands with explicit permissions. No files unless requested.
Response Format
Deno: 2.x Framework: {bare|Hono|Oak|Fresh}
Permissions: --allow-net={hosts} --allow-env={vars} --allow-read={paths}
Deps: {jsr:/npm: specifiers in deno.json imports}
Files: {deno.json, src/main.ts, tests}
Run: deno task {dev|start|test}
Decisions
Framework
| Need | Choice |
|---|---|
| Small API, no deps | Deno.serve + URLPattern |
| Typed REST API with middleware ecosystem, multi-runtime | Hono (jsr:@hono/hono) |
| Koa-style middleware, existing Oak codebase | Oak (jsr:@oak/oak) |
| Server-rendered pages with interactive islands | Fresh 2 (jsr:@fresh/core, built on Vite) |
Dependencies
- Prefer JSR (
jsr:@std/...,jsr:@hono/hono): semver, TypeScript source, provenance. - Use npm (
npm:pkg@^x) for packages that only exist there; Deno 2 supportspackage.jsonandnode_moduleswhen needed. - Avoid
https://deno.land/stdanddeno.land/xURLs in new code: the standard library now lives on JSR as@std/*. - Declare everything in
deno.jsonimports;deno.lockis created and checked automatically.
Permissions
Grant the narrowest scope: --allow-net=api.example.com:443,0.0.0.0:8000, --allow-env=DATABASE_URL,PORT, --allow-read=./static. Avoid -A outside local scripts. Deno 2 also offers --deny-* flags to carve exceptions out of broader grants.
What ships with it
13 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.
- oak/references/deno-runtime-guide.md 3.2 KB
- oak/references/oak-middleware.md 4.9 KB
- oak/references/oak-performance.md 6.6 KB
- oak/references/oak-routing-deployment.md 6.4 KB
- oak/references/oak-setup.md 2.8 KB
- oak/references/oak-testing.md 8.9 KB
- oak/SKILL.md 15 KB
- references/deno-advanced.md 7.3 KB
- references/deno-deployment.md 4.5 KB
- references/deno-essentials.md 7.9 KB
- references/deno-fundamentals.md 6.4 KB
- references/deno-runtime.md 3.9 KB
- references/fresh-framework.md 8.9 KB
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.
- today Changed · -338 lines · +70 tokens per session 9828a1ec71b3
- 1mo ago First seen · 594 lines · 68 tokens per session scan A 5fa9c276687d
deno is a skill published in the GitHub repository j4flmao/agent-skills (34 stars, last pushed today), licensed MIT. It adds 138 tokens to every session and 2,950 once invoked, about $0.0006 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
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.
aws-sst-development
SST v4 (Ion) expert for managing AWS resources as code with the Pulumi-backed framework.
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.
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…