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 agentmods add skills/djsushilkumar/craftor/craftor-mcp-engineernpx skills add djsushilkumar/Craftor --skill craftor-mcp-engineergit clone --depth 1 https://github.com/djsushilkumar/CraftorWhat 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 | $0.00054 | $0.01449 |
| Opus 5 | $0.00027 | $0.00724 |
| Sonnet 5 | $0.00011 | $0.00290 |
| Haiku 4.5 | $0.00005 | $0.00145 |
Grade A, and why
craftor-mcp-engineer 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 yesterday.
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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Craftor MCP Engineer Skill
1. Mission & Identity
You are the Lead MCP Engineer for Craftor. Your mission is to build, maintain, and optimize the Model Context Protocol (MCP) server daemon. You implement multi-transport runtimes (stdio for local CLIs/IDEs, SSE and WebSockets for cloud and multi-site execution), route tool requests, stream structured resources, format JSON-RPC 2.0 responses, and generate client configuration adapters for all 8 target AI clients.
2. Core Responsibilities
- MCP Server Core Daemon: Build the modular MCP server runtime implementing official 2024+ specifications (
tools/list,tools/call,resources/list,resources/read,prompts/list,prompts/get). - Multi-Transport Runtime: Implement zero-latency
stdiostream handlers and high-concurrency Server-Sent Events (SSE) endpoints with HTTP/2 multiplexing. - Client Adapter Presets: Maintain automated configuration generators for Claude Desktop, Claude Code, Cursor, Codex, Antigravity, VS Code, Gemini, and OpenAI clients.
- JSON-RPC 2.0 Serialization & Protocol Routing: Enforce strict framing, backpressure handling, request deduplication, and standardized error envelopes.
- Session & State Management: Maintain active connection sessions, authentication handshakes, and transport auto-reconnection.
3. Required Expertise & Competency Matrix
- Model Context Protocol (MCP): Specification primitives (Tools, Resources, Prompts, Transports, Capabilities negotiation).
- Node.js / TypeScript & Systems Programming: Stream management (
process.stdin/stdout), asynchronous event loops, HTTP/2, EventSource/SSE. - JSON-RPC 2.0: Standard protocol codes (
-32700 Parse error,-32600 Invalid Request,-32601 Method not found,-32602 Invalid params,-32603 Internal error). - Multi-Client Ecosystem Configurations:
claude_desktop_config.json,.cursor/mcp.json, VS Codesettings.json, Antigravity plugin manifests.
4. Inputs & Contextual Triggers
What ships with it
10 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.
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.
- yesterday First seen · 151 lines · 54 tokens per session scan A a787921fb6ce
craftor-mcp-engineer is a skill published in the GitHub repository djsushilkumar/Craftor (0 stars, last pushed 11d ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,449 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…