What is mcp-code-mode?

A TypeScript-based way to run external MCP tools, which are connectors that let an agent work with services such as ClickUp, Figma, databases, and browsers.

It is for orchestrating multi-step workflows across MCP-connected services, including project management, design, database, and browser tasks.

It reduces the amount of tool information the agent must keep in context and lets several tool calls share data in one run. It also provides type checks while the code is being written.

mcp-code-mode — Skill for Claude Code and OpenCode by MichelKerkmeeste

Install

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.

Any agent

npx skills add MichelKerkmeester/skilled-agent-harness_spec-driven-loops --skill mcp-code-mode

Clone the repo

git clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loops

Made for: Claude Code, 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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-code-mode/github.svg)](https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-code-mode)

Your own site

<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-code-mode"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-code-mode/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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-code-mode"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-code-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,005 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Privilege Escalation · line 86
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
high Privilege Escalation · line 342
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
high Privilege Escalation · line 384
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.

How audits are shown

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	$0.00033	$0.05005
Opus 5	$0.00016	$0.02502
Sonnet 5	$0.00007	$0.01001
Haiku 4.5	$0.00003	$0.00500

Measured 4d ago against content hash 537818677421, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-code-mode 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 4d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (mcp-server/index.ts, mcp-server/scripts/check-node.cjs, scripts/doctor.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.opencode/skills/mcp-code-mode/SKILL.md · 473 lines

How it starts

The opening of the file, as written. The whole thing — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Code Mode

Execute TypeScript code with direct access to 200+ MCP tools through progressive disclosure. Code Mode eliminates context overhead by loading tools on-demand, enabling complex multi-tool workflows in a single execution with state persistence and built-in error handling.

1. WHEN TO USE

Use Code Mode When

MANDATORY for ALL MCP tool calls:

✅ Calling ClickUp, Notion, Figma, MyService, Chrome DevTools, or any other MCP tools
✅ Accessing external APIs through MCP servers
✅ Managing tasks in project management tools
✅ Interacting with design tools, databases, or services
✅ Browser automation and web interactions

Benefits over traditional tool calling:

🚀 98.7% context reduction - 1.6k tokens vs 141k for 47 tools
⚡ 60% faster execution - Single execution vs 15+ API round trips
🔗 State persistence - Data flows naturally between operations
🛡️ Type safety - Full TypeScript support with autocomplete
🎯 Progressive loading - Tools discovered on-demand, zero upfront cost

Do NOT Use Code Mode For

Use native tools instead:

❌ File operations (use Read, Write, Edit tools)
❌ Text searching (use Grep tool)
❌ File discovery (use Glob tool)
❌ Bash commands (use Bash tool)
❌ Continuity recovery (use /speckit:resume, which walks handover.md -> _memory.continuity -> spec docs)

See Section 4 for details on Native MCP vs Code Mode distinction.

Common Use Cases

Scenario	Code Mode Approach	Benefit
Create ClickUp task	`call_tool_chain({ code: "await clickup.clickup_create_task({...})" })`	Type-safe, single execution
Multi-tool workflow	Figma → ClickUp → MyService in one execution	State persists, 5× faster
Browser automation	Chrome DevTools MCP for testing/screenshots	Sandboxed, reliable
Design-to-implementation	Fetch Figma design → Create task → Update CMS	Atomic workflow
External API access	Any MCP server (Notion, GitHub, etc.)	Progressive tool loading

Read the full file on GitHub · 473 lines

Files

What ships with it

60 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.

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.

4d ago Changed 537818677421
6d ago First seen · 473 lines · 33 tokens per session scan A d90794d6a952

Subscribe to this mod's changes

mcp-code-mode is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 5,005 once invoked, about $0.0002 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 2026-09-03.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens