What is mentor-agent?

Workshop instructions for running, testing, comparing, and troubleshooting MCP servers over local process, HTTP, or Express connections.

Use them when working with the workshop's stdio, HTTP, or Express MCP servers and their delivery, deployment, reference, and status tools.

They explain which servers start automatically, which must be started manually, and which dependencies and tools are required.

How leostacowskicompasso/workshop-27-08-26 configures OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to leostacowskicompasso/workshop-27-08-26. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/leostacowskicompasso/workshop-27-08-26/main/.opencode/skills/mentor-agent/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/leostacowskicompasso/workshop-27-08-26

Made for: OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/leostacowskicompasso/workshop-27-08-26/mentor-agent/github.svg)](https://agentmods.dev/skills/leostacowskicompasso/workshop-27-08-26/mentor-agent)

Your own site

<a href="https://agentmods.dev/skills/leostacowskicompasso/workshop-27-08-26/mentor-agent"><img src="https://agentmods.dev/badge/skills/leostacowskicompasso/workshop-27-08-26/mentor-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/leostacowskicompasso/workshop-27-08-26/mentor-agent"><img src="https://agentmods.dev/badge/skills/leostacowskicompasso/workshop-27-08-26/mentor-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,557 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00035	$0.02557
Opus 5	$0.00017	$0.01278
Sonnet 5	$0.00007	$0.00511
Haiku 4.5	$0.00003	$0.00256

Measured 10d ago against content hash 1450e2df05b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

mentor-agent scanned grade B with 1 finding 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

let res = await fetch('http://localhost:8787/', { method: 'POST',

.opencode/skills/mentor-agent/SKILL.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview (shared across all 3 transports)

SDK: @modelcontextprotocol/server (>= 2.0.0), @modelcontextprotocol/node (>= 2.0.0) — both required for HTTP/Express, only server for stdio.
Prerequisite: dependencies must already be installed (npm install / yarn install) at the repo root before running any server.
Startup model differs per transport:
- stdio_mcp is type: "local" in .opencode/opencode.jsonc (command: ["npm", "run", "start:stdio"]) — OpenCode spawns and manages this process automatically. Never instruct a participant to run npm run start:stdio manually.
- http_mcp (http://localhost:8787) and express_mcp (http://localhost:8788) are type: "remote" — OpenCode only connects, it does not start these. The participant must run npm run start:http / npm run start:express manually, each in its own terminal (the --watch flag blocks the terminal). Only after the server is up do the http_mcp*/express_mcp* tools appear.
All 4 tools (nordesul-delivery, nordesul-deploy, nordesul-reference, nordesul-status) are imported unconditionally by tools/index.js — no server starts until every one of them exports something.
Full SDK v2 reference: https://ts.sdk.modelcontextprotocol.io/v2/

stdio

Implementation Reference

https://ts.sdk.modelcontextprotocol.io/v2/serving/stdio.html

Implementation Dependencies

@modelcontextprotocol/server — McpServer
@modelcontextprotocol/server/stdio — serveStdio

Server Files

servers/stdio/main.js — entrypoint, registers the tools from tools/index.js via McpServer.registerTool and serves via serveStdio.
servers/stdio/config.js — SERVER.NAME/SERVER.VERSION, LOGGER.PREFIX.

How to Run

npm run start:stdio
# or
yarn start:stdio

How to Test Without Hanging

stdio doesn't use networking — send a JSON-RPC message via stdin in a single Node process (no --watch) and read the response from stdout. The process exits on its own once the input ends.

Read the full file on GitHub · 235 lines

Changes

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 · 235 lines · 35 tokens per session scan B 1450e2df05b7

Subscribe to this mod's changes

mentor-agent is a skill published in the GitHub repository leostacowskicompasso/workshop-27-08-26 (2 stars, last pushed 14d ago), licensed Unlicense. It adds 35 tokens to every session and 2,557 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents javascript mcp nodejs tools workshop

draft-release-notes

Author the committed release-notes file for a Prisma 8 release (stable or 8.0.0-rc.N) by enumerating the merged PRs since the previous release v tag (stable or -rc.N), resolving opaque TML-NNNN: titles via Linear context (never copied verbatim), triaging public-worthiness, and writing categorized notes — breaking…

prisma/orm · 174 tokens

record-upgrade-instructions

Record upgrade instructions alongside a Prisma Next breaking-change PR, so downstream consumers (users of @internal/ and authors of Prisma Next extensions) can apply the matching code translation automatically via the published upgrade skills. Use when you have refactored framework code and the test suite went red in…

prisma/orm · 120 tokens

create-pr

Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.

prisma/orm · 47 tokens

triage-contributor-pr

Triage open pull requests from external contributors to prisma/prisma and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming contributor PRs, to decide whether a fork PR is safe to run CI on, to check whether a PR is in scope for its version…

prisma/orm · 131 tokens

contrib-pr

Open a high-quality external contributor PR against prisma/orm. Use when the user is an outside contributor (not a Prisma maintainer) and wants to submit a change as a pull request from a fork. Encodes the contribution flow from CONTRIBUTING.md so the resulting PR passes review on the first round.

prisma/orm · 65 tokens

github-review-iteration

Orchestrates a GitHub PR review loop by delegating triage and implementation to dedicated sub-agents, then repeating until actionable review items are cleared. Use when the user says “address PR review”, “triage review comments”, or “iterate until review is clean”.

prisma/orm · 60 tokens

workshop-27-08-26: Skill for OpenCode