agentmods.dev

skilljack-mcp CLAUDE.md

skilljack-mcp CLAUDE.md is an instructions file for coding agents from olaservo/skilljack-mcp. It costs 4,395 tokens per session, scanned A, original, MIT.

Repository instructions for skilljack MCP, a TypeScript project whose server and browser interface use different MCP software versions.

In plain words
What is it for?
They are for developing, building, testing, and type-checking the Skilljack MCP server and its browser interface.
Why use it?
They document the build, test, type-check, development, and inspection commands, as well as the project’s split SDK setup.

Instructions file

not rated 16 2d ago A scan 4,395 tokens original MIT
View the source file olaservo/skilljack-mcp
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.

agentmods
npx agentmods add instructions/olaservo/skilljack-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/olaservo/skilljack-mcp

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.

agentmods badge for skilljack-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/olaservo/skilljack-mcp/claude-md.svg)](https://agentmods.dev/instructions/olaservo/skilljack-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/olaservo/skilljack-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/olaservo/skilljack-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,395 This file is loaded in full into every session.
When invoked 4,395 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.04395 $0.04395
Opus 5 $0.02197 $0.02197
Sonnet 5 $0.00879 $0.00879
Haiku 4.5 $0.00439 $0.00439

Measured 5d ago against content hash 6374d8ce3ecd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skilljack-mcp CLAUDE.md 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 5d 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.

CLAUDE.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skilljack MCP - Developer Guide

Commands

  • npm run build - Compile TypeScript to dist/ (Vite UI build + tsc)
  • npm run dev - Watch mode (tsx)
  • npm test - Run the vitest suite
  • npm run typecheck - Typecheck both halves (tsc --noEmit for the server, tsconfig.ui.json for src/ui)
  • npm run inspector - Test with MCP Inspector

CI (.github/workflows/ci.yml) runs npm ci, npm run build, and npm test on Node 20 for every push to main and every PR. Node 20+ is required (MCP TypeScript SDK v2 floor).

SDK split: server on v2, UI on v1

This package spans two independent bundles that share only the MCP wire format:

  • Server half (everything except src/ui/**) is on MCP TypeScript SDK v2 — @modelcontextprotocol/server, @modelcontextprotocol/server/stdio, @modelcontextprotocol/node (+ @modelcontextprotocol/client in tests only). Typechecked by the root tsconfig.json, which excludes src/ui/**.
  • Browser half (src/ui/mcp-app.ts, src/ui/skill-display.ts) is on @modelcontextprotocol/ext-apps + SDK v1, because ext-apps (latest 1.7.5) is hard-bound to v1 and has no v2-compatible release. Vite bundles it into self-contained HTML that runs in an iframe. Typechecked by tsconfig.ui.json (run by npm run build:ui).
  • @modelcontextprotocol/sdk (v1) and @modelcontextprotocol/ext-apps are devDependencies: they are needed to build the browser bundle, never to run the server.
  • src/ui-meta.ts is a vendored, faithful port of the three @modelcontextprotocol/ext-apps/server helpers the server used (registerAppTool, registerAppResource, getUiCapability), retyped against v2. It must keep emitting both _meta['ui/resourceUri'] and _meta.ui.resourceUri — hosts read either. Delete it when ext-apps ships a v2-compatible release.

No v1 object ever flows into v2 code in-process, so the two halves can stay on different major versions.

Configuration

Environment Variables:

  • SKILLS_DIR - Comma-separated list of skill directories
  • SKILLJACK_STATIC - Set to true, 1, or yes to enable static mode
  • MAX_FILE_SIZE_MB - Maximum file size for skill resources (default: 1MB)
  • WELL_KNOWN_ALLOWED_ORIGINS - Comma-separated origins (e.g. https://example.com) permitted as well-known publishers. Default-deny.
  • WELL_KNOWN_POLL_INTERVAL_MS - Well-known poll cadence (default 300000, 0 disables)
  • WELL_KNOWN_MAX_ARTIFACT_MB - Per-artifact byte cap (default 10)
  • WELL_KNOWN_MAX_UNPACKED_MB - Archive uncompressed size cap (default 50)
  • WELL_KNOWN_ALLOW_HTTP - 1/true/yes to permit http:// origins (dev only)
  • SKILLJACK_HTTP_PORT / SKILLJACK_HTTP - Serve over stateless HTTP instead of stdio (port, default 3000)
  • SKILLJACK_CATALOG - Catalog delivery channel: instructions (default) | tool-description (legacy, not recommended) — exactly one, never both

Read the full file on GitHub · 209 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.

  1. 5d ago First seen · 209 lines · 4,395 tokens per session scan A 6374d8ce3ecd

Subscribe to this mod's changes

skilljack-mcp CLAUDE.md is an instructions file published in the GitHub repository olaservo/skilljack-mcp (16 stars, last pushed 2d ago), licensed MIT. It adds 4,395 tokens to every session, about $0.0220 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,733 tokens