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 phughesmcr/deno-mcp-template --skill implementing-mcp-resourcesgit clone --depth 1 https://github.com/phughesmcr/deno-mcp-templateWrote 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/phughesmcr/deno-mcp-template/implementing-mcp-resources)<a href="https://agentmods.dev/skills/phughesmcr/deno-mcp-template/implementing-mcp-resources"><img src="https://agentmods.dev/badge/skills/phughesmcr/deno-mcp-template/implementing-mcp-resources/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/phughesmcr/deno-mcp-template/implementing-mcp-resources"><img src="https://agentmods.dev/badge/skills/phughesmcr/deno-mcp-template/implementing-mcp-resources.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00076 | $0.01602 |
| Opus 5 | $0.00038 | $0.00801 |
| Sonnet 5 | $0.00015 | $0.00320 |
| Haiku 4.5 | $0.00008 | $0.00160 |
Grade A, and why
implementing-mcp-resources 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 10d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementing MCP Resources
Workflow
Task Progress:
- [ ] Step 1: Create resource file in src/mcp/resources/
- [ ] Step 2: Define name, URI/template, config, and readCallback
- [ ] Step 3: Export as default ResourcePlugin or ResourceTemplatePlugin
- [ ] Step 4: Register in src/mcp/resources/mod.ts
- [ ] Step 5: (If KV-backed) Add URI-to-key mapping in kvKeys.ts
- [ ] Step 6: Run `deno task ci` to verify
Resource Types
| Type | Use Case | URI | Plugin Type |
|---|---|---|---|
| Static resource | Fixed content at a known URI | "hello://world" |
ResourcePlugin |
| KV-backed resource | Persistent, mutable state | "counter://value" |
ResourcePlugin |
| Resource template | Dynamic URI with variables | "greetings://{name}" |
ResourceTemplatePlugin |
Static Resource Template
Create a new file in src/mcp/resources/.
import type { ResourceMetadata } from "@modelcontextprotocol/sdk/server/mcp.js";
import type { ReadResourceResult } from "@modelcontextprotocol/sdk/types.js";
import type { ResourcePlugin } from "$/shared/types.ts";
const name = "myResource";
const uri = "my-scheme://my-path";
const config: ResourceMetadata = {
description: "What this resource provides",
mimeType: "text/plain", // or "application/json"
};
async function readCallback(): Promise<ReadResourceResult> {
return {
contents: [{
uri,
text: "Resource content here",
}],
};
}
const module: ResourcePlugin = {
type: "resource",
name,
uri,
config,
readCallback,
};
export default module;
Resource Template (Dynamic URI)
For resources with variable URI segments like greetings://{name}:
import {
type CompleteResourceTemplateCallback,
type ResourceMetadata,
ResourceTemplate,
} from "@modelcontextprotocol/sdk/server/mcp.js";
import type { ReadResourceResult } from "@modelcontextprotocol/sdk/types.js";
import type { ResourceTemplatePlugin } from "$/shared/types.ts";
const name = "myTemplate";
const completeName: CompleteResourceTemplateCallback = (value) => {
const prefix = value.trim().toLowerCase();
return suggestions.filter((s) => s.toLowerCase().startsWith(prefix)).slice(0, 5);
};
const template = new ResourceTemplate(
"my-scheme://{variable}",
{
list: undefined, // optional: callback to list all instances
complete: { variable: completeName }, // optional: autocomplete per variable
},
);
const config: ResourceMetadata = {
mimeType: "text/plain",
};
async function readCallback(
uri: URL,
variables: Record<string, unknown>,
): Promise<ReadResourceResult> {
const variable = variables.variable as string;
return {
contents: [{
uri: uri.toString(),
text: `Content for ${variable}`,
}],
};
}
const module: ResourceTemplatePlugin = {
type: "template",
name,
template,
config,
readCallback,
};
export default module;
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.
- 10d ago First seen · 246 lines · 76 tokens per session scan A db019b7bc271
implementing-mcp-resources is a skill published in the GitHub repository phughesmcr/deno-mcp-template (33 stars, last pushed 5mo ago), licensed MIT. It adds 76 tokens to every session and 1,602 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
api-security
Use for authorized security assessment of REST, GraphQL, WebSocket, or SOAP APIs, including discovery, authentication, authorization, rate-limit, and CI/CD testing.
protocol-reverse
Use for authorized reverse engineering of custom binary protocols, Protobuf/gRPC, WebSocket frames, and PCAP-driven protocol recovery.
building-mcp-servers
Use this skill whenever the user wants to design, build, harden, review, or debug an MCP (Model Context Protocol) server — including "build me an MCP server for X", connecting an AI agent/Claude to a database or API, adding tools/resources to an existing MCP server, reviewing a contributor PR against an MCP server, or…
Webhooks & Idempotency Audit
Comprehensive audit of ALL webhook handlers — Stripe and POD provider (Printify/Printful). Covers signature verification, idempotency guarantees, error isolation, retry safety, database transaction consistency, and monitoring. Use when asked to audit webhooks, idempotency, event handling, or webhook security.
Audit Plans Limits Monetization
Comprehensive audit of the SKAPARA subscription plans, usage limits, and monetization system. Use when asked to audit pricing, plans, usage limits, free tier, premium features, Stripe subscriptions, chat/design daily limits, upsell flows, or the €9.99/month plan. Covers server-side limit enforcement, bypass…
competition-graphql-rpc-drift
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for GraphQL schemas, persisted queries, RPC manifests, generated clients, OpenAPI drift, hidden operations, and contract-to-handler mismatches. Use when the user asks to inspect GraphQL or RPC requests, compare client contracts to live…