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 latestaiagents/agent-skills --skill mcp-resource-patternsgit clone --depth 1 https://github.com/latestaiagents/agent-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/latestaiagents/agent-skills/mcp-resource-patterns)<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/mcp-resource-patterns"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/mcp-resource-patterns/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/latestaiagents/agent-skills/mcp-resource-patterns"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/mcp-resource-patterns.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 | $0.00090 | $0.01260 |
| Opus 5.5 | $0.00036 | $0.00504 |
| Sonnet 5.5 | $0.00018 | $0.00252 |
| Haiku 4.5 | $0.00009 | $0.00126 |
Grade A, and why
mcp-resource-patterns 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 2mo 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Resource Patterns
Resources are read-only, URI-addressable data. Get them right and your server feels like a filesystem the agent can browse.
When to Use
- Deciding whether a read operation should be a tool or a resource
- Exposing hierarchical data (files, tickets, logs) to an agent
- Implementing live-updating data via subscriptions
- Designing URI schemes for a new MCP server
Tool vs Resource vs Prompt
| Aspect | Tool | Resource | Prompt |
|---|---|---|---|
| Invocation | Agent calls it | Agent reads it | User selects it |
| Side effects | Allowed | No | No |
| Addressing | Name + args | URI | Name |
| Result | Agent-chosen | User/agent-attached | Template expansion |
| Example | create_issue |
github://issues/123 |
/summarize-pr |
Rule of thumb: if the agent needs to decide whether to read it, it's a tool. If the user or agent needs to attach specific known data to context, it's a resource.
Static Resources
server.resource(
"changelog",
"file://changelog.md",
async () => ({
contents: [{
uri: "file://changelog.md",
mimeType: "text/markdown",
text: await fs.readFile("CHANGELOG.md", "utf-8"),
}],
}),
);
Templated Resources
Use URI templates (RFC 6570) for addressable collections:
server.resource(
"issue",
"github://repos/{owner}/{repo}/issues/{number}",
async (uri, { owner, repo, number }) => {
const issue = await gh.issues.get({ owner, repo, issue_number: +number });
return {
contents: [{
uri: uri.href,
mimeType: "application/json",
text: JSON.stringify(issue.data),
}],
};
},
);
The client auto-discovers the template and can fetch any matching URI.
Listing Resources
server.setRequestHandler(ListResourcesRequestSchema, async () => ({
resources: [
{ uri: "github://repos/acme/api/issues", name: "Open issues", mimeType: "application/json" },
{ uri: "github://repos/acme/api/prs", name: "Open PRs", mimeType: "application/json" },
],
}));
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.
- 2mo ago First seen · 153 lines · 90 tokens per session scan A 980e420761f7
mcp-resource-patterns is a skill published in the GitHub repository latestaiagents/agent-skills (6 stars, last pushed 2d ago), licensed MIT. It adds 90 tokens to every session and 1,260 once invoked, about $0.0004 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 2026-09-03.
mcp-resource-patterns compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-resource-patternslatestaiagents/agent-skills | Skill | 6 | 2d ago | MIT | A | 90 | Claude Code |
| fw-ai-actions-appfreshworks-developers/fw-dev-tools | Skill | 6 | 1mo ago | MIT | A | 123 | Claude Code |
| agent-raft-managerruvnet/ruflo | Skill | 81k | yesterday | MIT | A | 18 | Claude Code |
| nexent-daily-testModelEngine-Group/nexent | Skill | 6.1k | yesterday | MIT | A | 78 | Claude Code, Codex |
| moai-ref-api-patternsmodu-ai/moai-adk | Skill | 1.3k | 4d ago | Apache-2.0 | A | 85 | Claude Code |
| sinch-porting-apisinch/skills | Skill | 11 | 1mo ago | Apache-2.0 | A | 76 | Claude Code, Codex |
| sinch-voice-apisinch/skills | Skill | 11 | 1mo ago | Apache-2.0 | A | 92 | Claude Code, Codex |